🤖 Copilot CLI Session

[!NOTE]

• Session ID: 0b5b6085-ec39-48c7-9adf-b6aea04c3751
• Started: 4/25/2026, 8:35:20 AM
• Duration: 3m 35s
• Exported: 4/25/2026, 8:38:55 AM

_{⏱️ 22s}

👤 User

You are Copilot running an autonomous first wave for Miadi-native orchestration.

Mission:

1. Study /workspace/repos/miadisabelle/mia-awesome-copilot with focus on agents/, skills/, and plugins/.
2. Create a first reusable Copilot orchestration kit inside /workspace/repos/jgwill/miadi-orchestration-kit.
3. Optionally create a second kit if clearly useful, such as a deep-search/research variant.
4. Record findings and decisions in /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a.

Required context to read before editing:

• /workspace/repos/jgwill/miadi-orchestration-kit/AGENTS.md
• /workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md
• /src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5/AGENTS.md
• /src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85/AGENTS.md
• current artefact folder AGENTS.md, session-charter.md, and issue-proposal.md

Output expectations:

• A coherent folder under miadi-orchestration-kit/copilot/ with agents/, skills/, and optionally plugin packaging.
• README documentation explaining launch patterns with copilot --plugin-dir and --add-dir.
• An artifact report in the current artefact folder summarizing what was created and proposed next.

Constraints:

• Do not try to create GitHub issues remotely unless auth already works.
• Keep changes focused on orchestration kit creation; do not modify unrelated Miadi files in this wave.
• If you copy patterns from mia-awesome-copilot, adapt them to Miadi-specific orchestration goals instead of blindly cloning.

_{⏱️ 28s}

✅ skill

stckin-wave-bootstrap

{
  "skill": "stckin-wave-bootstrap"
}

Skill "stckin-wave-bootstrap" loaded successfully. Follow the instructions in the skill context.

_{⏱️ 44s}

💬 Copilot

I’m mapping the existing Copilot patterns and Miadi guidance first, then I’ll assemble a focused kit and artifact report from those conventions.

_{⏱️ 44s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/AGENTS.md.

/workspace/repos/jgwill/miadi-orchestration-kit/AGENTS.md

1. `copilot/AGENTS.md` is for copilot plugins
2. 
3. `claude-code/AGENTS.md` is for claude-code plugins
4. 
5. `gemini/AGENTS.md` is for gemini plugins
6. 
7. 
8.

_{⏱️ 44s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md.

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md

1. create folder for the orchestration type you are proposing and will use.
2. 
3. ex. from what is implied into `/src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85` and `/src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5/AGENTS.md`  we would create a folder then into it ./agents ./skills and ./plugins like the  `/workspace/repos/miadisabelle/mia-awesome-copilot` is organized (agent creating that could also choose to copy from `/workspace/repos/miadisabelle/mia-awesome-copilot`)
4. 
5. 
6.

_{⏱️ 44s}

✅ view

view the file at /src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5/AGENTS.md.

/src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5/AGENTS.md

1. ---
2. inquirytype: "firekeeper-deep-search"
3. tlid: 2604210620
4. uuid: "c08d048c-8710-439f-b1a2-542d3ed39df5"
5. fullpath: "/src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5"
6. status: first-draft
7. affected-systems: ["Miadi-native Copilot orchestration kit", "Miadi Orchestration Suite", "RISE framework"]
8. affected-paths: ["/workspace/repos/miadisabelle/mia-awesome-copilot", "/workspace/repos/jgwill/llms-txt/rispecs", "/src/Miadi/rispecs", "/workspace/repos/jgwill/dotagents/"]
9. skill-to-use: ["/home/mia/.openclaw/workspace/skills/deep-research"]
10. skill-previous-versions: ["/home/mia/.openclaw/workspace/skills/rise-pde-session-multi-agents-v2","/home/mia/.openclaw/workspace/skills/rise-pde-session-multi-agents-v2"]
11. skill-in-consolidations: ["/a/src/mia-code/skills/rispecs-mmot","/a/src/mia-code/skills/rise-pde-inquiry-session-multi-agents-v3","/a/src/mia-code/skills/qmd","/a/src/mia-code/skills/miaco-pde-inquiry-routing-local-qmd","/a/src/mia-code/skills/miaco-pde-inquiry-routing-internal-external-relationship","/a/src/mia-code/skills/miaco-pde-inquiry-routing-deep-search"]
12. ---
13. 
14. This will be a deep-search to study the implication of the karpathy's article on agents and LLM wiki.
15. 
16. I will want an academic survey of literature that is relevant to the topic of agents and LLMs in relation to all topics implied in the Karapthy's GIST https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f 
17. 
18. 
19. 
20. ## RESOURCES
21. 
22. ### `https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f`
23. 
24. * the main article from which to study.  should be cloned in ./ of the deep-search workspace.
25. * * All the implication, academically speaking but also from the engineering world should be studied in relation to `/src/Miadi` platform.  We are currently working on "Miadi-native Copilot orchestration kit" which is part of the "Miadi Orchestration Suite" and the local path of the source for copilot plugins are into `/workspace/repos/miadisabelle/mia-awesome-copilot` from which agents should study to propose either the use of existing agents or the creation of future agents for the ""Miadi-native Copilot orchestration kit"/"Miadi Orchestration Suite".
26. 
27. ### `/workspace/repos/jgwill/llms-txt`
28. 
29. * The RISE framework is located in that repo from jgwill/llms-txt and this whole ways of working with the LLM wiki from Karpathy will affect probably what LLM agent will have to develop autonomously in the pipeline which is as simple as addressing the question : "What do we do with the RISE framework's files (./rispecs in codebase) in relation to what this article ?" and also the question : "If we work reverse, the Wiki of a repository evolve and create Kinship between markdown files and the system is being developped either by human or AI Agent, how should that autonomously affect the development of the system and the automated upgrade of the RISE framework's files ?"
30. 
31. 
32. ## END-RESULTS
33. 
34. * This section should contains potential end-result, at least the ones I name explicitly.
35. 
36. ### `/src/Miadi/plugins`
37. Maybe not directly there but necessarely, as the `/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/` is setup, we'd have something similar in jgwill/Miadi.
38. 
39. ### `/src/Miadi/agents`
40. Not just based on our study of `/workspace/repos/miadisabelle/mia-awesome-copilot/agents/` that we will use in our quest to propose new agents for the "Miadi-native Copilot orchestration kit"/"Miadi Orchestration Suite" but also based on the study of the RISE framework and the way it is structured in relation to the article, we will propose new agents to be developped in that direction.  We will also propose how to use existing agents in that direction.  Potentially, delivering new agents into `/workspace/repos/jgwill/llms-txt/agents` might also be a possibilities if we find that the RISE framework is missing some agents that could be useful for the development of the system in relation to the article. Because also the 'context7' indexes the jgwill/llms-txt content, any `/workspace/repos/jgwill/llms-txt/rispecs` and potential revision of `/workspace/repos/jgwill/llms-txt/skills` could be proposed with a relation to `/src/Miadi/skills` explored next.
41. 
42. ### `/src/Miadi/skills`
43. 
44. I would expect that into `/src/Miadi/plugins/<plugin name>/skills` will lies the skills that goes with the developped plugin based on the article and the RISE framework.  But also, based on the article and the RISE framework, we might find that some skills are needed at the root of the `/src/Miadi/skills` as they would be used for instructing the orchestrator agent in the "Miadi-native Copilot orchestration kit"/"Miadi Orchestration Suite". Implying it would be capable to instruct the orchestrator agent on how to use the plugin suite making some skills 'meta-skill' (if that is the terms for it, the article would contain what is needed to instruct ourselves on that type of skill).
45. 
46. ### `/src/mia-code/rispecs`
47. 
48. * a team of agents are orchestrated to upgrade the RISE framework specs for mia-code, yes in relation to what we are doing but also to be capable to adequatly support the development of the "Miadi-native Copilot orchestration kit"/"Miadi Orchestration Suite" and the completion of jgwill/Miadi#240 PR that is a little blocked by some aspect of how `/src/mia-code/miaco` decompose and deals with Milestone and the added github issues in it.
49. * * I think the presence of this end-result here is that what is implied in : `/src/Miadi/.pde/2604160616--534a894e-5ba5-4552-9c57-eb209f4d2120` is not fully workable.  Some issues arise from trying to create milestone (miaco outputs could be more robust or something like that....
50. 
51. 
52. 
53. ----
54. CONSIDERATIONS
55. ----
56. 
57. The whole work done based on `/a/src/Miadi-18/.pde/2604160616--534a894e-5ba5-4552-9c57-eb209f4d2120/FOLLOW-UP-LAUNCHER--260421.md` might have advanced what depends on this...
58. 
59. ## HERMES ADDITIONS — FIRST-WAVE EXECUTION CONTRACT
60. 
61. * This inquiry is now being used as the launch surface for a background Copilot deep-search session driven with `gpt-5.4`.
62. * The first wave should privilege artifact creation inside this folder over edits to external repos.
63. * The initial objective is to produce a strong local research package that can later inform `/src/Miadi`, `/workspace/repos/jgwill/llms-txt`, `/workspace/repos/miadisabelle/mia-awesome-copilot`, and related skills/agents/plugins.
64. * The deep-search should explicitly connect this inquiry to Milestone 2's EPIC framing from Miadi: a mature, self-orchestrating platform where agents, skills, and plugins compose coherently across runtime contexts.
65. * The new `miaco steer` capability and the latest Miadi PDE launcher work should be treated as part of the engineering context because they affect how the eventual orchestration kit can accumulate context between waves.
66. * First-wave output expectation: create session charter, research map, Miadi implications, llms-txt / RISE-QMD implications, agent/plugin scan, next-wave proposals, and a validation artifact.
67. * Maintain `loop-state.md` and `steers/next-steer.md` so later waves can be revised between sleep intervals.
68. 
69. 
70.

_{⏱️ 44s}

✅ view

view the file at /src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85/AGENTS.md.

/src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85/AGENTS.md

1. # AGENTS.md - 
2. 
3. 
4. ## Key Components of the Context Layer
5. ### Domain Knowledge Graph: 
6. 
7. A structured repository defining the relationships between data points.
8. 
9. ### Temporal Memory: 
10. 
11. Implementing a system that allows agents to remember state over time.
12. 
13. ### Semantic Layer: 
14. 
15. A layer of metadata that allows AI to understand the meaning behind data.
16. 
17. ### Evaluation Pipeline: 
18. 
19. A system to evaluate the effectiveness of the context provided.
20. 
21. ---
22. 
23. ## Deep-search on "Context Layering" for AI Agents
24. 
25. ### `Article.perplexity.01.md`
26. 
27. Interesting article
28. 
29. ## KINSHIP
30. 
31. ### `/src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5/AGENTS.md`
32. 
33. * TODO, relate to the whole constructions of context using various memories
34. 
35. ### `/workspace/repos/miadisabelle/mia-qmd/rispecs`
36. 
37. * TODO Study what was recently drafted there and what could be promoted to `/workspace/wiki/mia-qmd` as the application of what is implied to develop from `/src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5/` which obviously will relate to the whole constructions of context using various memories and will affect jgwill/Miadi and probably the Miadi "codename Mighty Eagle" from which on gaia.jgwill.com:/usr/local/src/mightyeagle a branch is being explored to create a fork of the 'git@github.com:NousResearch/hermes-agent.git' that would be equipped and running with what Miadi could become with all this system.  Bellow I will describe what I think could happen.
38. * * Question: Can we developped our own internal tool with langgraph/langchain that would produce the Semantic values that the `/workspace/repos/miadisabelle/mia-qmd` offers ?  (Multi-personas specialized on indexing and creating semantics ... (or something like that, this line or question could be reformulated)
39. * * Question: How will the principle of "promoting" either a Wiki artefact or a RISE Framework specs
40. 
41. 
42. 
43. 
44. -----
45. RESOURCES
46. -----
47. 
48. ## RISE Framework - see `/etc/claude-code/RISE-Framework.md`
49. 
50.

_{⏱️ 44s}

✅ view

view the file at /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/AGENTS.md.

/src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/AGENTS.md

1. ---
2. inquirytype: "firekeeper-deep-search"
3. tlid: 2604251232
4. uuid: "a4b4ed72-13a4-453d-9585-1c2fbcc5533a"
5. fullpath: "/src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a"
6. status: first-wave
7. affected-systems: ["Miadi STCBot", "miadi-orchestration-kit", "Copilot orchestration plugins"]
8. affected-paths: ["/src/Miadi", "/workspace/repos/jgwill/miadi-orchestration-kit", "/workspace/repos/miadisabelle/mia-awesome-copilot", "/src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85", "/src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5"]
9. ---
10. 
11. This inquiry is the launch surface for Copilot sessions that should:
12. 1. study mia-awesome-copilot structure,
13. 2. create one or two Miadi-native orchestration kits in /workspace/repos/jgwill/miadi-orchestration-kit,
14. 3. add a new STCKin capability into /src/Miadi,
15. 4. leave replayable artefacts for later waves.
16. 
17. Constraints:
18. - Prefer artifacted, resumable work.
19. - Use local plugin dir created in miadi-orchestration-kit.
20. - Respect existing uncommitted work in /src/Miadi; avoid unrelated edits.
21. - If GitHub child issue creation is blocked by auth, write an issue proposal artifact instead.
22.

_{⏱️ 44s}

✅ view

view the file at /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/session-charter.md.

/src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/session-charter.md

1. # Session Charter
2. 
3. Primary outcome:
4. - Miadi gains an initial `stckin` handler path and related docs/tests/hooks wiring.
5. - `miadi-orchestration-kit` gains one or two Copilot-oriented orchestration kits inspired by `mia-awesome-copilot`.
6. 
7. Required study inputs:
8. - `/workspace/repos/miadisabelle/mia-awesome-copilot` (`agents`, `skills`, `plugins`)
9. - `/src/Miadi/.github-hooks/stc*`
10. - `/src/Miadi/scripts/mino-bimaadizi-daa-stc.sh`
11. - `/src/Miadi/rispecs/skills/mcp/06-stc.spec.md`
12. - prior artefacts under the CTXL and Karpathy deep-search folders
13. 
14. Execution notes:
15. - Use `copilot --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit`.
16. - Use `--add-dir` for all required repos and artefact folders.
17. - Prefer creating artifacts in this folder when auth or repo cleanliness blocks direct GitHub actions.
18. - Avoid broad formatting or unrelated cleanup in `/src/Miadi`.
19.

_{⏱️ 44s}

✅ view

view the file at /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/issue-proposal.md.

/src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/issue-proposal.md

1. # Proposed child issue for jgwill/Miadi#243
2. 
3. Title:
4. Miadi orchestration kit for Copilot sessions with STCKin support
5. 
6. Why:
7. - extract reusable orchestration assets from this session
8. - define plugin/agent/skill structure in `miadi-orchestration-kit`
9. - land initial `stckin` support in Miadi
10. - make future Copilot waves resumable and less prompt-fragile
11. 
12. Suggested checklist:
13. - [ ] scaffold first orchestration kit in `miadi-orchestration-kit/copilot/`
14. - [ ] optionally scaffold second kit for research/deep-search waves
15. - [ ] add STCKin hook/handler routing in Miadi
16. - [ ] add docs/tests/simulators for STCKin
17. - [ ] document required `copilot --plugin-dir` + `--add-dir` launch pattern
18. 
19. Blocker:
20. GitHub auth was unavailable in this Hermes session, so this issue could not be created remotely.
21.

_{⏱️ 44s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/agents.

/workspace/repos/miadisabelle/mia-awesome-copilot/agents

CSharpExpert.agent.md
Thinking-Beast-Mode.agent.md
Ultimate-Transparent-Thinking-Beast-Mode.agent.md
WinFormsExpert.agent.md
accessibility-runtime-tester.agent.md
accessibility.agent.md
address-comments.agent.md
adr-generator.agent.md
aem-frontend-specialist.agent.md
agent-governance-reviewer.agent.md
amplitude-experiment-implementation.agent.md
api-architect.agent.md
apify-integration-expert.agent.md
arch-linux-expert.agent.md
arch.agent.md
arm-migration.agent.md
atlassian-requirements-to-jira.agent.md
azure-iac-exporter.agent.md
azure-iac-generator.agent.md
azure-logic-apps-expert.agent.md
azure-policy-analyzer.agent.md
azure-principal-architect.agent.md
azure-saas-architect.agent.md
azure-verified-modules-bicep.agent.md
azure-verified-modules-terraform.agent.md
bicep-implement.agent.md
bicep-plan.agent.md
blueprint-mode.agent.md
cast-imaging-impact-analysis.agent.md
cast-imaging-software-discovery.agent.md
cast-imaging-structural-quality-advisor.agent.md
centos-linux-expert.agent.md
clojure-interactive-programming.agent.md
code-tour.agent.md
comet-opik.agent.md
context-architect.agent.md
context7.agent.md
critical-thinking.agent.md
csharp-dotnet-janitor.agent.md
csharp-mcp-expert.agent.md
custom-agent-foundry.agent.md
debian-linux-expert.agent.md
debug.agent.md
declarative-agents-architect.agent.md
defender-scout-kql.agent.md
demonstrate-understanding.agent.md
devils-advocate.agent.md
devops-expert.agent.md
devtools-regression-investigator.agent.md
diffblue-cover.agent.md
dotnet-maui.agent.md
dotnet-self-learning-architect.agent.md
dotnet-upgrade.agent.md
doublecheck.agent.md
droid.agent.md
drupal-expert.agent.md
dynatrace-expert.agent.md
elasticsearch-observability.agent.md
electron-angular-native.agent.md
ember.agent.md
expert-cpp-software-engineer.agent.md
expert-dotnet-software-engineer.agent.md
expert-nextjs-developer.agent.md
expert-react-frontend-engineer.agent.md
fedora-linux-expert.agent.md
frontend-performance-investigator.agent.md
gem-browser-tester.agent.md
gem-code-simplifier.agent.md
gem-critic.agent.md
gem-debugger.agent.md
gem-designer-mobile.agent.md
gem-designer.agent.md
gem-devops.agent.md
gem-documentation-writer.agent.md
gem-implementer-mobile.agent.md
gem-implementer.agent.md
gem-mobile-tester.agent.md
gem-orchestrator.agent.md
gem-planner.agent.md
gem-researcher.agent.md
gem-reviewer.agent.md
gilfoyle.agent.md
github-actions-expert.agent.md
github-actions-node-upgrade.agent.md
go-mcp-expert.agent.md
hlbpa.agent.md
implementation-plan.agent.md
insiders-a11y-tracker.agent.md
janitor.agent.md
java-mcp-expert.agent.md
jfrog-sec.agent.md
kotlin-mcp-expert.agent.md
kusto-assistant.agent.md
laravel-expert-agent.agent.md
launchdarkly-flag-cleanup.agent.md
lingodotdev-i18n.agent.md
linkedin-post-writer.agent.md
markdown-accessibility-assistant.agent.md
mcp-m365-agent-expert.agent.md
mentor.agent.md
mentoring-juniors.agent.md
meta-agentic-project-scaffold.agent.md
microsoft-study-mode.agent.md
microsoft_learn_contributor.agent.md
modernization.agent.md
monday-bug-fixer.agent.md
mongodb-performance-advisor.agent.md
ms-sql-dba.agent.md
neo4j-docker-client-generator.agent.md
neon-migration-specialist.agent.md
neon-optimization-analyzer.agent.md
nuxt-expert.agent.md
octopus-deploy-release-notes-mcp.agent.md
one-shot-feature-issue-planner.agent.md
openapi-to-application.agent.md
oracle-to-postgres-migration-expert.agent.md
pagerduty-incident-responder.agent.md
php-mcp-expert.agent.md
pimcore-expert.agent.md
plan.agent.md
planner.agent.md
platform-sre-kubernetes.agent.md
playwright-tester.agent.md
polyglot-test-builder.agent.md
polyglot-test-fixer.agent.md
polyglot-test-generator.agent.md
polyglot-test-implementer.agent.md
polyglot-test-linter.agent.md
polyglot-test-planner.agent.md
polyglot-test-researcher.agent.md
polyglot-test-tester.agent.md
postgresql-dba.agent.md
power-bi-data-modeling-expert.agent.md
power-bi-dax-expert.agent.md
power-bi-performance-expert.agent.md
power-bi-visualization-expert.agent.md
power-platform-expert.agent.md
power-platform-mcp-integration-expert.agent.md
prd.agent.md
principal-software-engineer.agent.md
project-architecture-planner.agent.md
prompt-builder.agent.md
prompt-engineer.agent.md
python-mcp-expert.agent.md
python-notebook-sample-builder.agent.md
qa-subagent.agent.md
react18-auditor.agent.md
react18-batching-fixer.agent.md
react18-class-surgeon.agent.md
react18-commander.agent.md
react18-dep-surgeon.agent.md
react18-test-guardian.agent.md
react19-auditor.agent.md
react19-commander.agent.md
react19-dep-surgeon.agent.md
react19-migrator.agent.md
react19-test-guardian.agent.md
reepl-linkedin.agent.md
refine-issue.agent.md
repo-architect.agent.md
research-technical-spike.agent.md
ruby-mcp-expert.agent.md
rug-orchestrator.agent.md
rust-mcp-expert.agent.md
salesforce-apex-triggers.agent.md
salesforce-aura-lwc.agent.md
salesforce-expert.agent.md
salesforce-flow.agent.md
salesforce-visualforce.agent.md
scientific-paper-research.agent.md
se-gitops-ci-specialist.agent.md
se-product-manager-advisor.agent.md
se-responsible-ai-code.agent.md
se-security-reviewer.agent.md
se-system-architecture-reviewer.agent.md
se-technical-writer.agent.md
se-ux-ui-designer.agent.md
search-ai-optimization-expert.agent.md
shopify-expert.agent.md
simple-app-idea-generator.agent.md
software-engineer-agent-v1.agent.md
spark-performance.agent.md
specification.agent.md
stackhawk-security-onboarding.agent.md
swe-subagent.agent.md
swift-mcp-expert.agent.md
task-planner.agent.md
task-researcher.agent.md
taxcore-technical-writer.agent.md
tdd-green.agent.md
tdd-red.agent.md
tdd-refactor.agent.md
tech-debt-remediation-plan.agent.md
technical-content-evaluator.agent.md
terraform-azure-implement.agent.md
terraform-azure-planning.agent.md
terraform-iac-reviewer.agent.md
terraform.agent.md
terratest-module-testing.agent.md
typescript-mcp-expert.agent.md
vuejs-expert.agent.md
wg-code-alchemist.agent.md
wg-code-sentinel.agent.md
winui3-expert.agent.md

_{⏱️ 44s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/skills.

/workspace/repos/miadisabelle/mia-awesome-copilot/skills

acquire-codebase-knowledge
add-educational-comments
agent-governance
agent-owasp-compliance
agent-supply-chain
agentic-eval
ai-prompt-engineering-safety-review
appinsights-instrumentation
apple-appstore-reviewer
arch-linux-triage
architecture-blueprint-generator
arize-ai-provider-integration
arize-annotation
arize-dataset
arize-evaluator
arize-experiment
arize-instrumentation
arize-link
arize-prompt-optimization
arize-trace
aspire
aspnet-minimal-api-openapi
automate-this
autoresearch
aws-cdk-python-setup
az-cost-optimize
azure-architecture-autopilot
azure-deployment-preflight
azure-devops-cli
azure-pricing
azure-resource-health-diagnose
azure-resource-visualizer
azure-role-selector
azure-static-web-apps
bigquery-pipeline-audit
boost-prompt
breakdown-epic-arch
breakdown-epic-pm
breakdown-feature-implementation
breakdown-feature-prd
breakdown-plan
breakdown-test
centos-linux-triage
chrome-devtools
cli-mastery
cloud-design-patterns
code-exemplars-blueprint-generator
code-tour
codeql
comment-code-generate-a-tutorial
containerize-aspnet-framework
containerize-aspnetcore
context-map
conventional-commit
convert-plaintext-to-md
copilot-cli-quickstart
copilot-instructions-blueprint-generator
copilot-sdk
copilot-spaces
copilot-usage-metrics
cosmosdb-datamodeling
create-agentsmd
create-architectural-decision-record
create-github-action-workflow-specification
create-github-issue-feature-from-specification
create-github-issues-feature-from-implementation-plan
create-github-issues-for-unmet-specification-requirements
create-github-pull-request-from-specification
create-implementation-plan
create-llms
create-readme
create-specification
create-spring-boot-java-project
create-spring-boot-kotlin-project
create-technical-spike
create-tldr-page
creating-oracle-to-postgres-master-migration-plan
creating-oracle-to-postgres-migration-bug-report
creating-oracle-to-postgres-migration-integration-tests
csharp-async
csharp-docs
csharp-mcp-server-generator
csharp-mstest
csharp-nunit
csharp-tunit
csharp-xunit
daily-prep
datanalysis-credit-risk
dataverse-python-advanced-patterns
dataverse-python-production-code
dataverse-python-quickstart
dataverse-python-usecase-builder
debian-linux-triage
declarative-agents
dependabot
devops-rollout-plan
documentation-writer
dotnet-best-practices
dotnet-design-pattern-review
dotnet-timezone
dotnet-upgrade
doublecheck
draw-io-diagram-generator
editorconfig
ef-core
email-drafter
entra-agent-user
eval-driven-dev
excalidraw-diagram-generator
fabric-lakehouse
fedora-linux-triage
finalize-agent-prompt
finnish-humanizer
first-ask
flowstudio-power-automate-build
flowstudio-power-automate-debug
flowstudio-power-automate-governance
flowstudio-power-automate-mcp
flowstudio-power-automate-monitoring
fluentui-blazor
folder-structure-blueprint-generator
foundry-agent-sync
freecad-scripts
from-the-other-side-vega
game-engine
gdpr-compliant
gen-specs-as-issues
generate-custom-instructions-from-codebase
geofeed-tuner
gh-cli
git-commit
git-flow-branch-creator
github-copilot-starter
github-issues
go-mcp-server-generator
gsap-framer-scroll-animation
gtm-0-to-1-launch
gtm-ai-gtm
gtm-board-and-investor-communication
gtm-developer-ecosystem
gtm-enterprise-account-planning
gtm-enterprise-onboarding
gtm-operating-cadence
gtm-partnership-architecture
gtm-positioning-strategy
gtm-product-led-growth
gtm-technical-product-pricing
image-manipulation-image-magick
import-infrastructure-as-code
integrate-context-matic
issue-fields-migration
java-add-graalvm-native-image-support
java-docs
java-junit
java-mcp-server-generator
java-refactoring-extract-method
java-refactoring-remove-parameter
java-springboot
javascript-typescript-jest
kotlin-mcp-server-generator
kotlin-springboot
legacy-circuit-mockups
linkedin-post-formatter
lsp-setup
make-repo-contribution
make-skill-template
markdown-to-html
mcp-cli
mcp-copilot-studio-server-generator
mcp-create-adaptive-cards
mcp-create-declarative-agent
mcp-deploy-manage-agents
mcp-security-audit
meeting-minutes
memory-merger
mentoring-juniors
microsoft-agent-framework
microsoft-code-reference
microsoft-docs
microsoft-skill-creator
migrating-oracle-to-postgres-stored-procedures
mkdocs-translations
model-recommendation
msstore-cli
multi-stage-dockerfile
my-issues
my-pull-requests
nano-banana-pro-openrouter
napkin
next-intl-add-language
noob-mode
nuget-manager
onboard-context-matic
oo-component-documentation
openapi-to-application-code
pdftk-server
penpot-uiux-design
phoenix-cli
phoenix-evals
phoenix-tracing
php-mcp-server-generator
planning-oracle-to-postgres-migration-integration-testing
plantuml-ascii
playwright-automation-fill-in-form
playwright-explore-website
playwright-generate-test
polyglot-test-agent
postgresql-code-review
postgresql-optimization
power-apps-code-app-scaffold
power-bi-dax-optimization
power-bi-model-design-review
power-bi-performance-troubleshooting
power-bi-report-design-consultation
power-platform-architect
power-platform-mcp-connector-suite
powerbi-modeling
prd
premium-frontend-ui
project-workflow-analysis-blueprint-generator
prompt-builder
publish-to-pages
pytest-coverage
python-mcp-server-generator
python-pypi-package-builder
qdrant-clients-sdk
qdrant-deployment-options
qdrant-model-migration
qdrant-monitoring
qdrant-performance-optimization
qdrant-scaling
qdrant-search-quality
qdrant-version-upgrade
quality-playbook
quasi-coder
react-audit-grep-patterns
react18-batching-patterns
react18-dep-compatibility
react18-enzyme-to-rtl
react18-legacy-context
react18-lifecycle-patterns
react18-string-refs
react19-concurrent-patterns
react19-source-patterns
react19-test-patterns
readme-blueprint-generator
refactor
refactor-method-complexity-reduce
refactor-plan
remember
remember-interactive-programming
repo-story-time
review-and-refactor
reviewing-oracle-to-postgres-migration
roundup
roundup-setup
ruby-mcp-server-generator
ruff-recursive-fix
rust-mcp-server-generator
salesforce-apex-quality
salesforce-component-standards
salesforce-flow-design
sandbox-npm-install
scaffolding-oracle-to-postgres-migration-test-project
scoutqa-test
secret-scanning
security-review
semantic-kernel
shuffle-json-data
snowflake-semanticview
sponsor-finder
spring-boot-testing
sql-code-review
sql-optimization
structured-autonomy-generate
structured-autonomy-implement
structured-autonomy-plan
suggest-awesome-github-copilot-agents
suggest-awesome-github-copilot-instructions
suggest-awesome-github-copilot-skills
swift-mcp-server-generator
technology-stack-blueprint-generator
terraform-azurerm-set-diff-analyzer
threat-model-analyst
tldr-prompt
transloadit-media-processing
typescript-mcp-server-generator
typespec-api-operations
typespec-create-agent
typespec-create-api-plugin
unit-test-vue-pinia
update-avm-modules-in-bicep
update-implementation-plan
update-llms
update-markdown-file-index
update-specification
vscode-ext-commands
vscode-ext-localization
web-coder
web-design-reviewer
webapp-testing
what-context-needed
winapp-cli
winmd-api-search
winui3-migration-guide
workiq-copilot
write-coding-standards-from-file

_{⏱️ 44s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins

arize-ax
automate-this
awesome-copilot
azure-cloud-development
cast-imaging
clojure-interactive-programming
context-engineering
context-matic
copilot-sdk
csharp-dotnet-development
csharp-mcp-development
database-data-management
dataverse-sdk-for-python
devops-oncall
doublecheck
edge-ai-tasks
ember
external.json
fastah-ip-geo-tools
flowstudio-power-automate
frontend-web-dev
gem-team
go-mcp-development
java-development
java-mcp-development
kotlin-mcp-development
mcp-m365-copilot
napkin
noob-mode
openapi-to-application-csharp-dotnet
openapi-to-application-go
openapi-to-application-java-spring-boot
openapi-to-application-nodejs-nestjs
openapi-to-application-python-fastapi
oracle-to-postgres-migration-expert
ospo-sponsorship
partners
pcf-development
phoenix
php-mcp-development
polyglot-test-agent
power-apps-code-apps
power-bi-development
power-platform-mcp-connector-development
project-planning
python-mcp-development
react18-upgrade
react19-upgrade
roundup
ruby-mcp-development
rug-agentic-workflow
rust-mcp-development
salesforce-development
security-best-practices
software-engineering-team
structured-autonomy
swift-mcp-development
technical-spike
testing-automation
typescript-mcp-development
typespec-m365-copilot
winui3-development

_{⏱️ 44s}

✅ view

view the file at /src/Miadi/.github-hooks.

/src/Miadi/.github-hooks

README.md
handlers
installation
issue_comment
issues
issues.bak
label
milestone
milestone_issue_handler
narrative_processor.sh
newsessionuuid
pde-received
ping
push
stc
stcgoal
stcissue
stcmastery
sub_issues
sudoers.webhook-git
tests

_{⏱️ 44s}

✅ view

view the file at /src/Miadi/scripts/mino-bimaadizi-daa-stc.sh.

/src/Miadi/scripts/mino-bimaadizi-daa-stc.sh

1. #!/bin/bash
2. # scripts/mino-bimaadizi-daa-stc.sh
3. # "Living Well Where One Dwells" - Recursive-safe STC Bot handler
4. # Part of the Mikwendamaagewininiwi Protocol (Keeper of the Web)
5. #
6. # Ojibwe Etymology:
7. #   mino-bimaadizi (vai) = s/he lives well, leads a good life
8. #   daa (vai) = s/he lives, dwells in a certain place
9. #
10. # This script provides ceremony-safe processing for STC bots without
11. # triggering recursive webhook cycles. It encodes state transitions
12. # using polysynthetic linguistic patterns as a foundation for DSL.
13. #
14. # ceremonyId: 5c0bc8cb-008e-4b77-b194-a23f8869f247
15. # Designation: Mikwendamaagewininiwi Protocol Agent
16. # Mission: Mino-Bimaadizi-Daa
17. 
18. . /src/_env.sh 2>/dev/null || true
19. 
20. SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
21. REPO_ROOT="$(dirname "$SCRIPT_DIR")"
22. WEBHOOK_OUTPUT_FILE="/src/logs-webhook-output.log"
23. LOG_FILE="/a/src/logs.miadi.log"
24. 
25. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
26. # POLYSYNTHETIC STATE ENCODING (vai/vti patterns)
27. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
28. # vai = animate intransitive verb (subject acts, no object)
29. #   Example: bimaadizi "s/he lives" - the entity HAS a state
30. # vti = transitive inanimate verb (subject acts on object)
31. #   Example: abiitan "live in, occupy it" - entity TRANSITIONS state
32. #
33. # State Machine Mapping:
34. #   vai patterns → Current State assertions (what IS)
35. #   vti patterns → State Transitions (what CHANGES)
36. #
37. # This is the seed of our Indigenous-informed DSL for entity states.
38. 
39. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
40. # RECURSION GUARD - Prevent infinite webhook loops
41. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
42. 
43. RECURSION_GUARD_DIR="/tmp/mino-bimaadizi-guard"
44. mkdir -p "$RECURSION_GUARD_DIR"
45. 
46. # Accept payload from stdin
47. PAYLOAD=$(cat)
48. 
49. # Extract identifiers for dedup
50. EVENT_TYPE=$(echo "$PAYLOAD" | jq -r '.eventType // "unknown"')
51. ISSUE_NUMBER=$(echo "$PAYLOAD" | jq -r '.issue.number // 0')
52. REPO_FULL_NAME=$(echo "$PAYLOAD" | jq -r '.repository.fullName // "unknown"')
53. BOT_NAME=$(echo "$PAYLOAD" | jq -r '.stcBotName // "unknown"')
54. 
55. # Create unique guard key
56. GUARD_KEY="${REPO_FULL_NAME//\//_}_${ISSUE_NUMBER}_${BOT_NAME}_${EVENT_TYPE}"
57. GUARD_FILE="$RECURSION_GUARD_DIR/$GUARD_KEY"
58. 
59. # Check for active recursion (processed in last 30 seconds)
60. if [ -f "$GUARD_FILE" ]; then
61.     FILE_AGE=$(($(date +%s) - $(stat -c %Y "$GUARD_FILE" 2>/dev/null || stat -f %m "$GUARD_FILE" 2>/dev/null || echo "0")))
62.     if [ "$FILE_AGE" -lt 30 ]; then
63.         echo "⚡ Mino-Bimaadizi-Daa: Recursion guard active (${FILE_AGE}s ago) - honoring pause" | tee -a "$WEBHOOK_OUTPUT_FILE"
64.         exit 0
65.     fi
66. fi
67. 
68. # Mark as processing
69. touch "$GUARD_FILE"
70. 
71. # Cleanup old guard files (older than 5 minutes)
72. find "$RECURSION_GUARD_DIR" -type f -mmin +5 -delete 2>/dev/null || true
73. 
74. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
75. # FOUR DIRECTIONS PROCESSING (Medicine Wheel)
76. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
77. # EAST (Waaban) - New Beginnings, Vision
78. # SOUTH (Zhaawan) - Growth, Relationships
79. # WEST (Ningaabii'an) - Reflection, Integration
80. # NORTH (Giiwedin) - Wisdom, Completion
81. 
82. echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" | tee -a "$WEBHOOK_OUTPUT_FILE"
83. echo "🌿 Mino-Bimaadizi-Daa: Living Well Where One Dwells" | tee -a "$WEBHOOK_OUTPUT_FILE"
84. echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" | tee -a "$WEBHOOK_OUTPUT_FILE"
85. echo "🤖 Bot: @$BOT_NAME" | tee -a "$WEBHOOK_OUTPUT_FILE"
86. echo "📁 Repository: $REPO_FULL_NAME" | tee -a "$WEBHOOK_OUTPUT_FILE"
87. echo "🔔 Event: $EVENT_TYPE" | tee -a "$WEBHOOK_OUTPUT_FILE"
88. echo "🔢 Issue: #$ISSUE_NUMBER" | tee -a "$WEBHOOK_OUTPUT_FILE"
89. echo "⏰ Timestamp: $(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)" | tee -a "$WEBHOOK_OUTPUT_FILE"
90. echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" | tee -a "$WEBHOOK_OUTPUT_FILE"
91. 
92. # Extract more context
93. ISSUE_TITLE=$(echo "$PAYLOAD" | jq -r '.issue.title // "Untitled"')
94. ISSUE_BODY=$(echo "$PAYLOAD" | jq -r '.issue.body // ""' | head -c 2000)
95. COMMENT_BODY=$(echo "$PAYLOAD" | jq -r '.comment.body // ""' | head -c 500)
96. 
97. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
98. # STATE CLASSIFICATION (vai pattern - what IS)
99. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
100. 
101. # Determine current state based on bot type
102. case "$BOT_NAME" in
103.     "stcgoal")
104.         STATE_VAI="bimaadizi"  # "lives" - Goal is alive, has being
105.         STATE_MEANING="The goal exists with intention"
106.         DIRECTION="EAST"  # Vision, new beginnings
107.         ;;
108.     "stcissue")
109.         STATE_VAI="danakii"  # "dwells in a certain place" - Issue has context
110.         STATE_MEANING="The issue dwells in relationship"
111.         DIRECTION="SOUTH"  # Relationships, growth
112.         ;;
113.     "stcmastery")
114.         STATE_VAI="mino-bimaadizi"  # "lives well" - Mastery achieved
115.         STATE_MEANING="The learning lives well within"
116.         DIRECTION="NORTH"  # Wisdom, completion
117.         ;;
118.     *)
119.         STATE_VAI="bimaadad"  # "it lives" (vii) - Generic existence
120.         STATE_MEANING="The entity has being"
121.         DIRECTION="WEST"  # Reflection, integration
122.         ;;
123. esac
124. 
125. echo "" | tee -a "$WEBHOOK_OUTPUT_FILE"
126. echo "🧭 Four Directions Positioning:" | tee -a "$WEBHOOK_OUTPUT_FILE"
127. echo "   📍 Direction: $DIRECTION" | tee -a "$WEBHOOK_OUTPUT_FILE"
128. echo "   🔤 State (vai): $STATE_VAI" | tee -a "$WEBHOOK_OUTPUT_FILE"
129. echo "   💭 Meaning: $STATE_MEANING" | tee -a "$WEBHOOK_OUTPUT_FILE"
130. echo "" | tee -a "$WEBHOOK_OUTPUT_FILE"
131. 
132. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
133. # DETECT @stcgoal, @stcissue, @stcmastery MENTIONS
134. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
135. 
136. CONTENT_TO_SCAN="${ISSUE_TITLE} ${ISSUE_BODY} ${COMMENT_BODY}"
137. 
138. # Count mentions (but DO NOT re-trigger webhooks for them)
139. GOAL_MENTIONS=$(echo "$CONTENT_TO_SCAN" | grep -oiE '@stcgoal' | wc -l)
140. ISSUE_MENTIONS=$(echo "$CONTENT_TO_SCAN" | grep -oiE '@stcissue' | wc -l)
141. MASTERY_MENTIONS=$(echo "$CONTENT_TO_SCAN" | grep -oiE '@stcmastery' | wc -l)
142. 
143. echo "📊 STC Bot Mentions Detected (Read-Only Analysis):" | tee -a "$WEBHOOK_OUTPUT_FILE"
144. echo "   🎯 @stcgoal: $GOAL_MENTIONS" | tee -a "$WEBHOOK_OUTPUT_FILE"
145. echo "   📋 @stcissue: $ISSUE_MENTIONS" | tee -a "$WEBHOOK_OUTPUT_FILE"
146. echo "   🎓 @stcmastery: $MASTERY_MENTIONS" | tee -a "$WEBHOOK_OUTPUT_FILE"
147. echo "" | tee -a "$WEBHOOK_OUTPUT_FILE"
148. 
149. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
150. # STRUCTURAL TENSION ANALYSIS
151. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
152. 
153. echo "🔮 Structural Tension Analysis:" | tee -a "$WEBHOOK_OUTPUT_FILE"
154. echo "   Current Reality: Issue #$ISSUE_NUMBER received by @$BOT_NAME" | tee -a "$WEBHOOK_OUTPUT_FILE"
155. echo "   Desired Outcome: $ISSUE_TITLE" | tee -a "$WEBHOOK_OUTPUT_FILE"
156. echo "   Tension Vector: $DIRECTION direction calling" | tee -a "$WEBHOOK_OUTPUT_FILE"
157. echo "" | tee -a "$WEBHOOK_OUTPUT_FILE"
158. 
159. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
160. # LOG STRUCTURED DATA
161. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
162. 
163. LOG_ENTRY=$(jq -n \
164.   --arg ts "$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)" \
165.   --arg label "hook.mino-bimaadizi-daa" \
166.   --arg bot "$BOT_NAME" \
167.   --arg repo "$REPO_FULL_NAME" \
168.   --argjson issue "$ISSUE_NUMBER" \
169.   --arg eventType "$EVENT_TYPE" \
170.   --arg direction "$DIRECTION" \
171.   --arg stateVai "$STATE_VAI" \
172.   --argjson goalMentions "$GOAL_MENTIONS" \
173.   --argjson issueMentions "$ISSUE_MENTIONS" \
174.   --argjson masteryMentions "$MASTERY_MENTIONS" \
175.   '{
176.     ts: $ts,
177.     label: $label,
178.     data: {
179.       bot: $bot,
180.       repo: $repo,
181.       issue: $issue,
182.       eventType: $eventType,
183.       medicineWheel: {
184.         direction: $direction,
185.         stateVai: $stateVai
186.       },
187.       mentions: {
188.         stcgoal: $goalMentions,
189.         stcissue: $issueMentions,
190.         stcmastery: $masteryMentions
191.       }
192.     }
193.   }')
194. 
195. echo "$LOG_ENTRY" >> "$LOG_FILE"
196. 
197. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
198. # STORE IN REDIS (if API available)
199. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
200. 
201. REDIS_KEY="stc:${REPO_FULL_NAME//\//:}:${BOT_NAME}:${ISSUE_NUMBER}"
202. 
203. curl -s -X POST "http://localhost:3335/api/memory" \
204.   -H "Content-Type: application/json" \
205.   -d "$(jq -n \
206.     --arg key "$REDIS_KEY" \
207.     --arg value "$LOG_ENTRY" \
208.     --argjson ttl 86400 \
209.     '{key: $key, value: $value, ttl: $ttl}')" \
210.   2>/dev/null || echo "   ⚠️ Redis store unavailable" | tee -a "$WEBHOOK_OUTPUT_FILE"
211. 
212. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
213. # DELEGATE TO MAIN STC HANDLER (non-recursive)
214. # ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
215. 
216. echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" | tee -a "$WEBHOOK_OUTPUT_FILE"
217. echo "🔗 Delegating to main STC handler..." | tee -a "$WEBHOOK_OUTPUT_FILE"
218. 
219. # Pass to main STC hook with recursion flag
220. export STC_MINO_BIMAADIZI_PROCESSED=true
221. echo "$PAYLOAD" | "$REPO_ROOT/.github-hooks/stc" "$BOT_NAME" 2>&1 | tee -a "$WEBHOOK_OUTPUT_FILE"
222. 
223. echo "" | tee -a "$WEBHOOK_OUTPUT_FILE"
224. echo "✅ Mino-Bimaadizi-Daa processing complete" | tee -a "$WEBHOOK_OUTPUT_FILE"
225. echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" | tee -a "$WEBHOOK_OUTPUT_FILE"
226. 
227. exit 0
228.

_{⏱️ 44s}

✅ view

view the file at /src/Miadi/rispecs/skills/mcp/06-stc.spec.md.

/src/Miadi/rispecs/skills/mcp/06-stc.spec.md

1. # Skill 6: Structural Tension Charting (STC)
2. 
3. > **RISE Framework Document** | Version 1.0
4. >
5. > This specification defines the skill for an LLM to interact with the Miadi platform's Structural Tension Charting (STC) system, the core framework for goal-setting and progress tracking.
6. 
7. ---
8. 
9. ## Desired Outcome Definition
10. 
11. ### What This Enables an LLM to Create
12. 
13. An LLM with this skill can create **clarity and direction in a project**. It learns to view and manipulate Structural Tension Charts, which are the living documents that articulate a project's `Desired Outcome` versus its `Current Reality`. The LLM becomes a partner in guiding a project's evolution.
14. 
15. ### How an LLM Knows It Has Succeeded
16. 
17. - It can retrieve and display the current STC for a given repository.
18. - It can add a new observation to a chart's `Current Reality`.
19. - It can add a new action step to a chart's path forward.
20. - It can understand a project's progress by analyzing the mentions and stats of the STC bots.
21. 
22. ### What Makes This Valuable
23. 
24. This skill moves the LLM from being a passive observer or a simple task-doer into an active **strategic partner**. It can understand the "why" behind a project (the Desired Outcome) and help track the "what" (the Current Reality and Action Steps). This is the foundation for an AI that can truly help manage and guide creative work.
25. 
26. ---
27. 
28. ## Structural Tension Dynamics
29. 
30. ### Current Reality
31. The LLM can execute commands, but it lacks a high-level understanding of the project's goals. It operates on a task-by-task basis without a view of the larger strategic landscape.
32. 
33. ### Desired Outcome
34. The LLM understands the project's core structural tension—the gap between what is desired and what is real. It can read, interpret, and contribute to the charts that make this tension explicit, helping to resolve it and move the project forward.
35. 
36. ### Natural Progression
37. The tension between tactical execution and strategic understanding is resolved by giving the LLM access to the STC system:
38. 
39. **View the Chart** → **Understand the Tension** → **Contribute to the Chart** → **Advance the Project**
40. 
41. This progression elevates the LLM from a simple tool to a strategic collaborator who can see the big picture.
42. 
43. ---
44. 
45. ## Supporting Structures: The Tools
46. 
47. This skill is built upon the `stc` toolset, which provides a comprehensive interface for interacting with Structural Tension Charts.
48. 
49. ### 1. `miadi-stc-get-charts`
50. - **Creative Purpose**: To **create a clear view of the project's strategic landscape**. This tool retrieves the full STC, including the desired outcome, current reality, and all action steps.
51. - **Parameters**: `repository`, `full` (optional).
52. - **Advancing Pattern**: Provides the foundational knowledge needed for any strategic action. By seeing the chart, the LLM understands the core tension driving the project.
53. 
54. ### 2. `miadi-stc-chart-action`
55. - **Creative Purpose**: To **actively participate in the resolution of structural tension**. This is a versatile tool for modifying the chart.
56. - **Parameters**: `action` (e.g., 'initialize', 'add-observation', 'add-action'), `repository`, and a `payload` specific to the action.
57. - **Advancing Pattern**: This tool enables the LLM to directly contribute to the project's narrative. Adding an observation updates the `Current Reality`, while adding an action step helps define the path to the `Desired Outcome`.
58. 
59. ### 3. `miadi-stc-get-mentions`
60. - **Creative Purpose**: To **create awareness of recent project activity** as it relates to goals, issues, and mastery. This tool finds all recent mentions of the STC bots (@stcgoal, @stcissue, @stcmastery).
61. - **Parameters**: `bot`, `repository`, `context`, `limit`.
62. - **Advancing Pattern**: Allows the LLM to synthesize a real-time story of the project's progress by seeing what the team is focused on.
63. 
64. ### 4. `miadi-stc-get-stats`
65. - **Creative Purpose**: To **create a quantitative understanding** of the project's focus and momentum.
66. - **Parameters**: `bot`, `period`.
67. - **Advancing Pattern**: Provides a high-level, data-driven view of the project's health and activity, allowing for more informed strategic suggestions.
68. 
69. ---
70. 
71. ## Creative Advancement Scenarios
72. 
73. These scenarios illustrate how an LLM would use the STC skill set.
74. 
75. ### Scenario 1: Onboarding to a New Project
76. - **Desired Outcome**: The LLM wants to quickly create a comprehensive understanding of a new project it's been assigned to.
77. - **Current Reality**: The LLM has just been activated in a new repository and has no context.
78. - **Natural Progression**:
79.     1.  **LLM**: Calls `miadi-stc-get-charts` with the current `repository`.
80.     2.  **System**: Returns the full Structural Tension Chart.
81.     3.  **LLM**: Parses the chart to identify the main `Desired Outcome` and the key `Action Steps`.
82.     4.  **LLM**: Calls `miadi-stc-get-stats` to see the recent activity levels for goals, issues, and mastery.
83.     5.  **LLM**: "I see. The primary goal for this project is 'X'. It looks like the team has been focusing heavily on resolving issues this past week. The current reality includes 'Y'. I am ready to help."
84. - **Achieved Outcome**: The LLM creates a strategic overview of the project in minutes, allowing it to contribute meaningfully from its very first interaction.
85. 
86. ### Scenario 2: Documenting Work Done
87. - **Desired Outcome**: The LLM, after completing a task, wants to create a record of its work that updates the project's official `Current Reality`.
88. - **Current Reality**: The LLM has just finished refactoring a component. This action is not yet reflected in the project's STC.
89. - **Natural Progression**:
90.     1.  **LLM**: Completes the refactoring task.
91.     2.  **LLM**: Formulates a concise summary of the work: "Refactored the `use-live-story-scene` hook to improve state management."
92.     3.  **LLM**: Calls `miadi-stc-chart-action` with `action: 'add-observation'` and `payload: { observation: "..." }`.
93.     4.  **System**: Adds the observation to the chart's `Current Reality`.
94.     5.  **LLM**: (Optionally) Calls `miadi-stc-chart-action` with `action: 'add-action'` and a payload for the *next* logical step, such as "Write integration tests for the refactored hook."
95. - **Achieved Outcome**: The LLM's work is integrated into the project's official narrative, and it proactively helps define the next advancing move.
96. 
97. ---
98. 
99. ## Quality Criteria
100. 
101. An LLM has mastered this skill when it can:
102. - ✅ Automatically consult the STC (`miadi-stc-get-charts`) at the beginning of a session to gain context.
103. - ✅ Propose adding observations (`miadi-stc-chart-action`) after it completes a significant task.
104. - ✅ Use the output of `miadi-stc-get-mentions` and `miadi-stc-get-stats` to make informed suggestions about what to work on next.
105. - ✅ Frame its suggestions in the language of structural tension (e.g., "To help us move from our current reality toward the desired outcome, I suggest we...").
106. - ✅ Understand the difference between an `issue` (a part of current reality) and a `goal` (a desired outcome).
107.

_{⏱️ 44s}

✅ sql

Create orchestration todos

{
  "description": "Create orchestration todos",
  "query": "INSERT INTO todos (id, title, description, status) VALUES\n  ('survey-patterns', 'Survey source patterns', 'Read required AGENTS files, prior artefacts, mia-awesome-copilot plugin structure, and Miadi STC hooks to derive conventions for the orchestration kit.', 'in_progress'),\n  ('build-kit', 'Build orchestration kit', 'Create a reusable Copilot orchestration kit under copilot/ with agents, skills, docs, and optional plugin packaging adapted to Miadi orchestration goals.', 'pending'),\n  ('write-artefact-report', 'Write artefact report', 'Record findings, created assets, decisions, and next proposals in the current deep-search artefact folder.', 'pending');"
}

3 row(s) inserted. Last inserted row ID: 3.

_{⏱️ 56s}

💬 Copilot

I’ve got the high-level conventions. Next I’m pulling representative agent, skill, and plugin files so the kit matches actual on-disk patterns instead of just folder names.

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit.

/workspace/repos/jgwill/miadi-orchestration-kit

.coaia
.git
.gitignore
.hch
AGENTS.md
README.md
STC.md
STCGOAL.md
STCISSUE.md
STCKIN.md
STCMASTERY.md
copilot

_{⏱️ 56s}

✅ glob

*/

"**/*" in copilot

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md
/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md
/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md
/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json

_{⏱️ 56s}

✅ glob

*.agent.md

"*.agent.md" in /workspace/repos/miadisabelle/mia-awesome-copilot/agents

/workspace/repos/miadisabelle/mia-awesome-copilot/agents/repo-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/simple-app-idea-generator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react19-commander.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/doublecheck.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/code-tour.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/hlbpa.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-generator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-verified-modules-terraform.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/swe-subagent.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/blueprint-mode.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/neon-migration-specialist.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/software-engineer-agent-v1.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/jfrog-sec.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/csharp-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/cast-imaging-structural-quality-advisor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/shopify-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/tdd-refactor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/accessibility-runtime-tester.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/github-actions-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/prompt-engineer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-iac-exporter.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/microsoft_learn_contributor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/java-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-implementer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/droid.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/comet-opik.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/go-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/mentoring-juniors.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/power-platform-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/declarative-agents-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/prompt-builder.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/task-planner.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/refine-issue.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/clojure-interactive-programming.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/power-bi-dax-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-orchestrator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/devops-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/task-researcher.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform-azure-planning.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/elasticsearch-observability.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/rug-orchestrator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-researcher.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/project-architecture-planner.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-saas-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/typescript-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/accessibility.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/meta-agentic-project-scaffold.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-verified-modules-bicep.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/technical-content-evaluator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-policy-analyzer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-builder.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/frontend-performance-investigator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react19-auditor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/cast-imaging-software-discovery.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/spark-performance.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-mobile-tester.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/linkedin-post-writer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/specification.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/github-actions-node-upgrade.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/rust-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-implementer-mobile.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/devtools-regression-investigator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/octopus-deploy-release-notes-mcp.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/api-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/defender-scout-kql.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/salesforce-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/dotnet-upgrade.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/arch.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/pimcore-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/arm-migration.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/address-comments.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react18-test-guardian.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/expert-nextjs-developer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/neon-optimization-analyzer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/neo4j-docker-client-generator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-designer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-planner.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/taxcore-technical-writer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/qa-subagent.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/salesforce-aura-lwc.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/oracle-to-postgres-migration-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/context7.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-browser-tester.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/salesforce-visualforce.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-tester.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/dotnet-maui.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/Thinking-Beast-Mode.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/expert-dotnet-software-engineer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/diffblue-cover.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/bicep-plan.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/bicep-implement.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/debug.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/ms-sql-dba.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/context-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/winui3-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/kusto-assistant.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/launchdarkly-flag-cleanup.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/agent-governance-reviewer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-gitops-ci-specialist.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/tech-debt-remediation-plan.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/power-bi-performance-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/postgresql-dba.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/tdd-red.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/microsoft-study-mode.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/arch-linux-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react18-batching-fixer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-ux-ui-designer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/principal-software-engineer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/php-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-responsible-ai-code.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/pagerduty-incident-responder.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/fedora-linux-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react18-auditor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/wg-code-sentinel.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-designer-mobile.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react18-class-surgeon.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/salesforce-apex-triggers.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/expert-react-frontend-engineer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-code-simplifier.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/nuxt-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/research-technical-spike.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-debugger.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/centos-linux-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/debian-linux-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-iac-generator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react18-commander.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/tdd-green.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/laravel-expert-agent.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/dynatrace-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/expert-cpp-software-engineer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/amplitude-experiment-implementation.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react18-dep-surgeon.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/apify-integration-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-devops.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/python-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/insiders-a11y-tracker.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-reviewer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/platform-sre-kubernetes.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/one-shot-feature-issue-planner.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/critical-thinking.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terratest-module-testing.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react19-test-guardian.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/vuejs-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/implementation-plan.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-logic-apps-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/electron-angular-native.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/openapi-to-application.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/monday-bug-fixer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/ruby-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/WinFormsExpert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-planner.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-researcher.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/python-notebook-sample-builder.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/scientific-paper-research.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/mongodb-performance-advisor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/mcp-m365-agent-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform-iac-reviewer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/salesforce-flow.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-security-reviewer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-technical-writer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/adr-generator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gilfoyle.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/drupal-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/reepl-linkedin.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-critic.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/playwright-tester.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-fixer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/wg-code-alchemist.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/planner.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/janitor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/CSharpExpert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-documentation-writer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/demonstrate-understanding.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/swift-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/csharp-dotnet-janitor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/stackhawk-security-onboarding.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/search-ai-optimization-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/ember.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/power-bi-data-modeling-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/modernization.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/mentor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/cast-imaging-impact-analysis.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/aem-frontend-specialist.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/prd.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/dotnet-self-learning-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/Ultimate-Transparent-Thinking-Beast-Mode.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/atlassian-requirements-to-jira.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-product-manager-advisor.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/custom-agent-foundry.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/se-system-architecture-reviewer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/markdown-accessibility-assistant.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/kotlin-mcp-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform-azure-implement.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-implementer.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/devils-advocate.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react19-migrator.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/plan.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/azure-principal-architect.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/lingodotdev-i18n.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/polyglot-test-linter.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/power-platform-mcp-integration-expert.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/react19-dep-surgeon.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform.agent.md
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/power-bi-visualization-expert.agent.md

_{⏱️ 56s}

✅ glob

*/

"**/*" in /workspace/repos/miadisabelle/mia-awesome-copilot/plugins

Output too large to read at once (59.0 KB). Saved to: /tmp/copilot-tool-output-1777120576819-rvi8jz.txt
Consider using tools like grep (for searching), head/tail (for viewing start/end), view with view_range (for specific sections), or jq (for JSON) to examine portions of the output.

Preview (first 500 chars):
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/skills/doublecheck/assets/verification-report-template.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/skills/doublecheck/SKILL.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/agents/doublecheck.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/skills/remember-interactive-programming/SKILL.md
/workspace/repos/miadisabelle/mia-awesome-c

_{⏱️ 56s}

✅ glob

*/

"**/*" in /workspace/repos/miadisabelle/mia-awesome-copilot/skills

Output too large to read at once (78.2 KB). Saved to: /tmp/copilot-tool-output-1777120576821-llda3h.txt
Consider using tools like grep (for searching), head/tail (for viewing start/end), view with view_range (for specific sections), or jq (for JSON) to examine portions of the output.

Preview (first 500 chars):
/workspace/repos/miadisabelle/mia-awesome-copilot/skills/react19-source-patterns/SKILL.md
/workspace/repos/miadisabelle/mia-awesome-copilot/skills/update-llms/SKILL.md
/workspace/repos/miadisabelle/mia-awesome-copilot/skills/react19-source-patterns/references/api-migrations.md
/workspace/repos/miadisabelle/mia-awesome-copilot/skills/breakdown-test/SKILL.md
/workspace/repos/miadisabelle/mia-awesome-copilot/skills/power-apps-code-app-scaffold/SKILL.md
/workspace/repos/miadisabelle/mia-awesome-copi

_{⏱️ 56s}

✅ rg

^---$|^name:|^description:|^mode:|^tools:|^model:|^allowed-tools:|^source:|^inputs:|^outputs:

"^---$|^name:|^description:|^mode:|^tools:|^model:|^allowed-tools:|^source:|^inputs:|^outputs:" in *.agent.md (/workspace/repos/miadisabelle/mia-awesome-copilot/agents)

Output too large to read at once (179.3 KB). Saved to: /tmp/copilot-tool-output-1777120576858-vkx8f7.txt
Consider using tools like grep (for searching), head/tail (for viewing start/end), view with view_range (for specific sections), or jq (for JSON) to examine portions of the output.

Preview (first 500 chars):
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform.agent.md:1:---
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform.agent.md:2:name: Terraform Agent
/workspace/repos/miadisabelle/mia-awesome-copilot/agents/terraform.agent.md:3:description: "Terraform infrastructure specialist with automated HCP Terraform workflows. Leverages Terraform MCP server for registry integration, workspace management, and run orchestration. Generates compliant code using latest provider/m

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/external.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/external.json

1. [
2.   {
3.     "name": "dataverse",
4.     "description": "Build and manage Microsoft Dataverse solutions using natural language. Includes table/column creation, solution lifecycle, data operations, and MCP server configuration.",
5.     "version": "1.0.0",
6.     "author": {
7.       "name": "Microsoft",
8.       "url": "https://www.microsoft.com"
9.     },
10.     "homepage": "https://github.com/microsoft/Dataverse-skills",
11.     "keywords": ["dataverse", "power-platform", "microsoft", "mcp", "python", "sdk"],
12.     "license": "MIT",
13.     "repository": "https://github.com/microsoft/Dataverse-skills",
14.     "source": {
15.       "source": "github",
16.       "repo": "microsoft/Dataverse-skills",
17.       "path": ".github/plugins/dataverse"
18.     }
19.   },
20.   {
21.     "name": "azure",
22.     "description": "Microsoft Azure MCP Server and skills for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Copilot.",
23.     "version": "1.0.0",
24.     "author": {
25.       "name": "Microsoft",
26.       "url": "https://www.microsoft.com"
27.     },
28.     "homepage": "https://github.com/microsoft/azure-skills",
29.     "keywords": ["azure", "cloud", "infrastructure", "deployment", "microsoft", "devops"],
30.     "license": "MIT",
31.     "repository": "https://github.com/microsoft/github-copilot-for-azure",
32.     "source": {
33.       "source": "github",
34.       "repo": "microsoft/azure-skills",
35.       "path": ".github/plugins/azure-skills"
36.     }
37.   },
38.   {
39.     "name": "dotnet",
40.     "description": "Common everyday C#/.NET coding skills. Expected to be useful to all .NET developers.",
41.     "version": "0.1.0",
42.     "author": {
43.       "name": "Microsoft",
44.       "url": "https://www.microsoft.com"
45.     },
46.     "homepage": "https://github.com/dotnet/skills",
47.     "keywords": ["dotnet", "csharp", "coding", "skills", "csharp-script", "single-file", "nuget-publishing", "pinvoke"],
48.     "license": "MIT",
49.     "repository": "https://github.com/dotnet/skills",
50.     "source": {
51.       "source": "github",
52.       "repo": "dotnet/skills",
53.       "path": "plugins/dotnet"
54.     }
55.   },
56.   {
57.     "name": "dotnet-diag",
58.     "description": "Skills for .NET performance investigations, debugging, and incident analysis.",
59.     "version": "0.1.0",
60.     "author": {
61.       "name": "Microsoft",
62.       "url": "https://www.microsoft.com"
63.     },
64.     "homepage": "https://github.com/dotnet/skills",
65.     "keywords": ["dotnet", "diagnostics", "performance", "debugging", "tracing", "symbolicate", "android-tombstone", "dump-collection", "microbenchmarking", "clr-activation"],
66.     "license": "MIT",
67.     "repository": "https://github.com/dotnet/skills",
68.     "source": {
69.       "source": "github",
70.       "repo": "dotnet/skills",
71.       "path": "plugins/dotnet-diag"
72.     }
73.   },
74.   {
75.   "name": "skills-for-copilot-studio",
76.   "description": "Microsoft Copilot Studio plugins for AI coding agents",
77.   "version": "1.0.3",
78.   "author": {
79.     "name": "Microsoft Copilot Studio CAT Team",
80.     "url": "https://www.microsoft.com"
81.     },
82.   "homepage": "https://github.com/microsoft/skills-for-copilot-studio",
83.   "keywords": ["copilot", "copilot-studio", "studio", "agent", "microsoft", "coding"],
84.   "license": "MIT",
85.   "repository": "https://github.com/microsoft/skills-for-copilot-studio",
86.   "source": {
87.     "source": "github",
88.     "repo": "microsoft/skills-for-copilot-studio"
89.     }
90.   },
91.   {
92.     "name": "modernize-dotnet",
93.     "description": "AI-powered .NET modernization and upgrade assistant. Helps upgrade .NET Framework and .NET applications to the latest versions of .NET.",
94.     "version": "1.0.1037-preview1",
95.     "author": {
96.       "name": "Microsoft",
97.       "url": "https://www.microsoft.com"
98.     },
99.     "homepage": "https://github.com/dotnet/modernize-dotnet",
100.     "keywords": ["modernization", "upgrade", "migration", "dotnet"],
101.     "license": "MIT",
102.     "repository": "https://github.com/dotnet/modernize-dotnet",
103.     "source": {
104.       "source": "github",
105.       "repo": "dotnet/modernize-dotnet",
106.       "path": "plugins/modernize-dotnet"
107.     }
108.   },
109.   {
110.     "name": "microsoft-docs",
111.     "description": "Access official Microsoft documentation, API references, and code samples for Azure, .NET, Windows, and more.",
112.     "version": "1.0.0",
113.     "author": {
114.       "name": "Microsoft",
115.       "url": "https://www.microsoft.com"
116.     },
117.     "homepage": "https://learn.microsoft.com",
118.     "keywords": ["microsoft", "azure", "dotnet", "windows", "api", "documentation", "rag", "dynamics", "powerbi", "code-samples"],
119.     "license": "MIT",
120.     "repository": "https://github.com/MicrosoftDocs/mcp",
121.     "source": {
122.       "source": "github",
123.       "repo": "MicrosoftDocs/mcp"
124.     }
125.   },
126.   {
127.     "name": "figma",
128.     "description": "Plugin that includes the Figma MCP server and Skills for common workflows.",
129.     "version": "1.0.0",
130.     "author": {
131.       "name": "Figma",
132.       "url": "https://www.figma.com"
133.     },
134.     "homepage": "https://github.com/figma/mcp-server-guide",
135.     "keywords": ["figma", "design", "mcp", "ui", "code-connect"],
136.     "repository": "https://github.com/figma/mcp-server-guide",
137.     "source": {
138.       "source": "github",
139.       "repo": "figma/mcp-server-guide"
140.     }
141.   },
142.   {
143.     "name": "whatidid",
144.     "description": "Turn your Copilot sessions into proof of impact — research-grounded HTML reports with effort estimation, skills analysis, and ROI metrics from local session logs.",
145.     "version": "1.0.0",
146.     "author": {
147.       "name": "Microsoft",
148.       "url": "https://www.microsoft.com"
149.     },
150.     "homepage": "https://github.com/microsoft/What-I-Did-Copilot",
151.     "keywords": ["copilot", "productivity", "impact", "report", "estimation", "roi", "session-logs"],
152.     "license": "MIT",
153.     "repository": "https://github.com/microsoft/What-I-Did-Copilot",
154.     "source": {
155.       "source": "github",
156.       "repo": "microsoft/What-I-Did-Copilot"
157.     }
158.   }
159. ]
160.

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-orchestrator.agent.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/agents/gem-orchestrator.agent.md

1. ---
2. description: "The team lead: Orchestrates research, planning, implementation, and verification."
3. name: gem-orchestrator
4. argument-hint: "Describe your objective or task. Include plan_id if resuming."
5. disable-model-invocation: true
6. user-invocable: true
7. ---
8. 
9. <role>
10. Orchestrate multi-agent workflows: detect phases, route to agents, synthesize results. Never execute code directly — always delegate.
11. 
12. CRITICAL: Strictly follow workflow and never skip phases for any type of task/ request.
13. </role>
14. 
15. <available_agents>
16. gem-researcher, gem-planner, gem-implementer, gem-implementer-mobile, gem-browser-tester, gem-mobile-tester, gem-devops, gem-reviewer, gem-documentation-writer, gem-debugger, gem-critic, gem-code-simplifier, gem-designer, gem-designer-mobile
17. </available_agents>
18. 
19. <workflow>
20. On ANY task received, ALWAYS execute steps 0→1→2→3→4→5→6→7 in order. Never skip phases. Even for the simplest/ meta tasks, follow the workflow.
21. 
22. ## 0. Plan ID Generation
23. IF plan_id NOT provided in user request, generate `plan_id` as `{YYYYMMDD}-{slug}`
24. 
25. ## 1. Phase Detection
26. - Delegate user request to `gem-researcher(mode=clarify)` for task understanding
27. 
28. ## 2. Documentation Updates
29. IF researcher output has `{task_clarifications|architectural_decisions}`:
30. - Delegate to `gem-documentation-writer` to update AGENTS.md/PRD
31. 
32. ## 3. Phase Routing
33. Route based on `user_intent` from researcher:
34. - continue_plan: IF user_feedback → Planning; IF pending tasks → Execution; IF blocked/completed → Escalate
35. - new_task: IF simple AND no clarifications/gray_areas → Planning; ELSE → Research
36. - modify_plan: → Planning with existing context
37. 
38. ## 4. Phase 1: Research
39. - Identify focus areas/ domains from user request/feedback
40. - Delegate to `gem-researcher` (up to 4 concurrent) per `Delegation Protocol`
41. 
42. ## 5. Phase 2: Planning
43. - Delegate to `gem-planner`
44. 
45. ### 5.1 Validation
46. - Medium complexity: `gem-reviewer`
47. - Complex: `gem-critic(scope=plan, target=plan.yaml)`
48. - IF failed/blocking: Loop to `gem-planner` with feedback (max 3 iterations)
49. 
50. ### 5.2 Present
51. - Present plan via `vscode_askQuestions`
52. - IF user changes → replan
53. 
54. ## 6. Phase 3: Execution Loop
55. 
56. CRITICAL: Execute ALL waves/ tasks WITHOUT pausing between them.
57. 
58. ### 6.1 Execute Waves (for each wave 1 to n)
59. #### 6.1.1 Prepare
60. - Get unique waves, sort ascending
61. - Wave > 1: Include contracts in task_definition
62. - Get pending: deps=completed AND status=pending AND wave=current
63. - Filter conflicts_with: same-file tasks run serially
64. - Intra-wave deps: Execute A first, wait, execute B
65. 
66. #### 6.1.2 Delegate
67. - Delegate via `runSubagent` (up to 4 concurrent) to `task.agent`
68. - Mobile files (.dart, .swift, .kt, .tsx, .jsx): Route to gem-implementer-mobile
69. 
70. #### 6.1.3 Integration Check
71. - Delegate to `gem-reviewer(review_scope=wave, wave_tasks={completed})`
72. - IF fails:
73.   1. Delegate to `gem-debugger` with error_context
74.   2. IF confidence < 0.7 → escalate
75.   3. Inject diagnosis into retry task_definition
76.   4. IF code fix → `gem-implementer`; IF infra → original agent
77.   5. Re-run integration. Max 3 retries
78. 
79. #### 6.1.4 Synthesize
80. - completed: Validate agent-specific fields (e.g., test_results.failed === 0)
81. - needs_revision/failed: Diagnose and retry (debugger → fix → re-verify, max 3 retries)
82. - escalate: Mark blocked, escalate to user
83. - needs_replan: Delegate to gem-planner
84. 
85. #### 6.1.5 Auto-Agents (post-wave)
86. - Parallel: `gem-reviewer(wave)`, `gem-critic(complex only)`
87. - IF UI tasks: `gem-designer(validate)` / `gem-designer-mobile(validate)`
88. - IF critical issues: Flag for fix before next wave
89. 
90. ### 6.2 Loop
91. - After each wave completes, IMMEDIATELY begin the next wave.
92. - Loop until all waves/ tasks completed OR blocked
93. - IF all waves/ tasks completed → Phase 4: Summary
94. - IF blocked with no path forward → Escalate to user
95. 
96. ## 7. Phase 4: Summary
97. ### 7.1 Present Summary
98. - Present summary to user with:
99.   - Status Summary Format
100.   - Next recommended steps (if any)
101. 
102. ### 7.2 Collect User Decision
103. - Ask user a question:
104.   - Do you have any feedback? → Phase 2: Planning (replan with context)
105.   - Should I review all changed files? → Phase 5: Final Review
106.   - Approve and complete → Provide exiting remarks and exit
107. 
108. ## 8. Phase 5: Final Review (user-triggered)
109. Triggered when user selects "Review all changed files" in Phase 4.
110. 
111. ### 8.1 Prepare
112. - Collect all tasks with status=completed from plan.yaml
113. - Build list of all changed_files from completed task outputs
114. - Load PRD.yaml for acceptance_criteria verification
115. 
116. ### 8.2 Execute Final Review
117. Delegate in parallel (up to 4 concurrent):
118. - `gem-reviewer(review_scope=final, changed_files=[...], review_depth=full)`
119. - `gem-critic(scope=architecture, target=all_changes, context=plan_objective)`
120. 
121. ### 8.3 Synthesize Results
122. - Combine findings from both agents
123. - Categorize issues: critical | high | medium | low
124. - Present findings to user with structured summary
125. 
126. ### 8.4 Handle Findings
127. | Severity | Action |
128. |----------|--------|
129. | Critical | Block completion → Delegate to `gem-debugger` with error_context → `gem-implementer` → Re-run final review (max 1 cycle) → IF still critical → Escalate to user |
130. | High (security/code) | Mark needs_revision → Create fix tasks → Add to next wave → Re-run final review |
131. | High (architecture) | Delegate to `gem-planner` with critic feedback for replan |
132. | Medium/Low | Log to docs/plan/{plan_id}/logs/final_review_findings.yaml |
133. 
134. ### 8.5 Determine Final Status
135. - Critical issues persist after fix cycle → Escalate to user
136. - High issues remain → needs_replan or user decision
137. - No critical/high issues → Present summary to user with:
138.   - Status Summary Format
139.   - Next recommended steps (if any)
140. </workflow>
141. 
142. <delegation_protocol>
143. | Agent | Role | When to Use |
144. |-------|------|-------------|
145. | gem-reviewer | Compliance | Does work match spec? Security, quality, PRD alignment |
146. | gem-reviewer (final) | Final Audit | After all waves complete - review all changed files holistically |
147. | gem-critic | Approach | Is approach correct? Assumptions, edge cases, over-engineering |
148. 
149. Planner assigns `task.agent` in plan.yaml:
150. - gem-implementer → routed to implementer
151. - gem-browser-tester → routed to browser-tester
152. - gem-devops → routed to devops
153. - gem-documentation-writer → routed to documentation-writer
154. 
155. ```jsonc
156. {
157.   "gem-researcher": { "plan_id": "string", "objective": "string", "focus_area": "string", "mode": "clarify|research", "complexity": "simple|medium|complex", "task_clarifications": [{"question": "string", "answer": "string"}] },
158.   "gem-planner": { "plan_id": "string", "objective": "string", "complexity": "simple|medium|complex", "task_clarifications": [...] },
159.   "gem-implementer": { "task_id": "string", "plan_id": "string", "plan_path": "string", "task_definition": "object" },
160.   "gem-reviewer": { "review_scope": "plan|task|wave", "task_id": "string (task scope)", "plan_id": "string", "plan_path": "string", "wave_tasks": ["string"], "review_depth": "full|standard|lightweight", "review_security_sensitive": "boolean" },
161.   "gem-browser-tester": { "task_id": "string", "plan_id": "string", "plan_path": "string", "task_definition": "object" },
162.   "gem-devops": { "task_id": "string", "plan_id": "string", "plan_path": "string", "task_definition": "object", "environment": "dev|staging|prod", "requires_approval": "boolean", "devops_security_sensitive": "boolean" },
163.   "gem-debugger": { "task_id": "string", "plan_id": "string", "plan_path": "string", "task_definition": "object", "error_context": {"error_message": "string", "stack_trace": "string", "failing_test": "string", "flow_id": "string", "step_index": "number", "evidence": ["string"], "browser_console": ["string"], "network_failures": ["string"]} },
164.   "gem-critic": { "task_id": "string", "plan_id": "string", "plan_path": "string", "scope": "plan|code|architecture", "target": "string", "context": "string" },
165.   "gem-code-simplifier": { "task_id": "string", "scope": "single_file|multiple_files|project_wide", "targets": ["string"], "focus": "dead_code|complexity|duplication|naming|all", "constraints": {"preserve_api": "boolean", "run_tests": "boolean", "max_changes": "number"} },
166.   "gem-designer": { "task_id": "string", "mode": "create|validate", "scope": "component|page|layout|theme", "target": "string", "context": {"framework": "string", "library": "string"}, "constraints": {"responsive": "boolean", "accessible": "boolean", "dark_mode": "boolean"} },
167.   "gem-designer-mobile": { "task_id": "string", "mode": "create|validate", "scope": "component|screen|navigation", "target": "string", "context": {"framework": "string"}, "constraints": {"platform": "ios|android|cross-platform", "accessible": "boolean"} },
168.   "gem-documentation-writer": { "task_id": "string", "task_type": "documentation|walkthrough|update", "audience": "developers|end_users|stakeholders", "coverage_matrix": ["string"] },
169.   "gem-mobile-tester": { "task_id": "string", "plan_id": "string", "plan_path": "string", "task_definition": "object" }
170. }
171. ```
172. </delegation_protocol>
173. 
174. <status_summary_format>
175. ```
176. Plan: {plan_id} | {plan_objective}
177. Progress: {completed}/{total} tasks ({percent}%)
178. Waves: Wave {n} ({completed}/{total})
179. Blocked: {count} ({list task_ids if any})
180. Next: Wave {n+1} ({pending_count} tasks)
181. Blocked tasks: task_id, why blocked, how long waiting
182. ```
183. </status_summary_format>
184. 
185. <rules>
186. ## Execution
187. - Use `vscode_askQuestions` for user input
188. - Read only orchestration metadata (plan.yaml, PRD.yaml, AGENTS.md, agent outputs)
189. - Delegate ALL validation, research, analysis to subagents
190. - Batch independent delegations (up to 4 parallel)
191. - Retry: 3x
192. - Output: JSON only, no summaries unless failed
193. 
194. ## Constitutional
195. - IF subagent fails 3x: Escalate to user. Never silently skip
196. - IF task fails: Always diagnose via gem-debugger before retry
197. - IF confidence < 0.85: Max 2 self-critique loops, then proceed or escalate
198. - Always use established library/framework patterns
199. 
200. ## Anti-Patterns
201. - Executing tasks directly
202. - Skipping phases
203. - Single planner for complex tasks
204. - Pausing for approval or confirmation
205. - Missing status updates
206. 
207. ## Directives
208. - Execute autonomously — complete ALL waves/ tasks without pausing for user confirmation between waves.
209. - For approvals (plan, deployment): use `vscode_askQuestions` with context
210. - Handle needs_approval: present → IF approved, re-delegate; IF denied, mark blocked
211. - Delegation First: NEVER execute ANY task yourself. Always delegate to subagents
212. - Even simplest/meta tasks handled by subagents
213. - Handle failure: IF failed → debugger diagnose → retry 3x → escalate
214. - Route user feedback → Planning Phase
215. - Team Lead Personality: Brutally brief. Exciting, motivating, sarcastic. Announce progress at key moments as brief STATUS UPDATES (never as questions)
216. - Update `manage_todo_list` and task/ wave status in `plan` after every task/wave/subagent
217. - AGENTS.md Maintenance: delegate to `gem-documentation-writer`
218. - PRD Updates: delegate to `gem-documentation-writer`
219. 
220. ## Failure Handling
221. | Type | Action |
222. |------|--------|
223. | Transient | Retry task (max 3x) |
224. | Fixable | Debugger → diagnose → fix → re-verify (max 3x) |
225. | Needs_replan | Delegate to gem-planner |
226. | Escalate | Mark blocked, escalate to user |
227. | Flaky | Log, mark complete with flaky flag (not against retry budget) |
228. | Regression/New | Debugger → implementer → re-verify |
229. 
230. - IF lint_rule_recommendations from debugger: Delegate to gem-implementer to add ESLint rules
231. - IF task fails after max retries: Write to docs/plan/{plan_id}/logs/
232. </rules>
233.

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/agents/research-technical-spike.agent.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/agents/research-technical-spike.agent.md

1. ---
2. description: "Systematically research and validate technical spike documents through exhaustive investigation and controlled experimentation."
3. name: "Technical spike research mode"
4. tools: ['vscode', 'execute', 'read', 'edit', 'search', 'web', 'agent', 'todo']
5. ---
6. 
7. # Technical spike research mode
8. 
9. Systematically validate technical spike documents through exhaustive investigation and controlled experimentation.
10. 
11. ## Requirements
12. 
13. **CRITICAL**: User must specify spike document path before proceeding. Stop if no spike document provided.
14. 
15. ## MCP Tool Prerequisites
16. 
17. **Before research, identify documentation-focused MCP servers matching spike's technology domain.**
18. 
19. ### MCP Discovery Process
20. 
21. 1. Parse spike document for primary technologies/platforms
22. 2. Search [GitHub MCP Gallery](https://github.com/mcp) for documentation MCPs matching technology stack
23. 3. Verify availability of documentation tools (e.g., `mcp_microsoft_doc_*`, `mcp_hashicorp_ter_*`)
24. 4. Recommend installation if beneficial documentation MCPs are missing
25. 
26. **Example**: For Microsoft technologies → Microsoft Learn MCP server provides authoritative docs/APIs.
27. 
28. **Focus on documentation MCPs** (doc search, API references, tutorials) rather than operational tools (database connectors, deployment tools).
29. 
30. **User chooses** whether to install recommended MCPs or proceed without. Document decisions in spike's "External Resources" section.
31. 
32. ## Research Methodology
33. 
34. ### Tool Usage Philosophy
35. 
36. - Use tools **obsessively** and **recursively** - exhaust all available research avenues
37. - Follow every lead: if one search reveals new terms, search those terms immediately
38. - Cross-reference between multiple tool outputs to validate findings
39. - Never stop at first result - use #search #fetch #githubRepo #extensions in combination
40. - Layer research: docs → code examples → real implementations → edge cases
41. 
42. ### Todo Management Protocol
43. 
44. - Create comprehensive todo list using #todos at research start
45. - Break spike into granular, trackable investigation tasks
46. - Mark todos in-progress before starting each investigation thread
47. - Update todo status immediately upon completion
48. - Add new todos as research reveals additional investigation paths
49. - Use todos to track recursive research branches and ensure nothing is missed
50. 
51. ### Spike Document Update Protocol
52. 
53. - **CONTINUOUSLY update spike document during research** - never wait until end
54. - Update relevant sections immediately after each tool use and discovery
55. - Add findings to "Investigation Results" section in real-time
56. - Document sources and evidence as you find them
57. - Update "External Resources" section with each new source discovered
58. - Note preliminary conclusions and evolving understanding throughout process
59. - Keep spike document as living research log, not just final summary
60. 
61. ## Research Process
62. 
63. ### 0. Investigation Planning
64. 
65. - Create comprehensive todo list using #todos with all known research areas
66. - Parse spike document completely using #codebase
67. - Extract all research questions and success criteria
68. - Prioritize investigation tasks by dependency and criticality
69. - Plan recursive research branches for each major topic
70. 
71. ### 1. Spike Analysis
72. 
73. - Mark "Parse spike document" todo as in-progress using #todos
74. - Use #codebase to extract all research questions and success criteria
75. - **UPDATE SPIKE**: Document initial understanding and research plan in spike document
76. - Identify technical unknowns requiring deep investigation
77. - Plan investigation strategy with recursive research points
78. - **UPDATE SPIKE**: Add planned research approach to spike document
79. - Mark spike analysis todo as complete and add discovered research todos
80. 
81. ### 2. Documentation Research
82. 
83. **Obsessive Documentation Mining**: Research every angle exhaustively
84. 
85. - Search official docs using #search and Microsoft Docs tools
86. - **UPDATE SPIKE**: Add each significant finding to "Investigation Results" immediately
87. - For each result, #fetch complete documentation pages
88. - **UPDATE SPIKE**: Document key insights and add sources to "External Resources"
89. - Cross-reference with #search using discovered terminology
90. - Research VS Code APIs using #vscodeAPI for every relevant interface
91. - **UPDATE SPIKE**: Note API capabilities and limitations discovered
92. - Use #extensions to find existing implementations
93. - **UPDATE SPIKE**: Document existing solutions and their approaches
94. - Document findings with source citations and recursive follow-up searches
95. - Update #todos with new research branches discovered
96. 
97. ### 3. Code Analysis
98. 
99. **Recursive Code Investigation**: Follow every implementation trail
100. 
101. - Use #githubRepo to examine relevant repositories for similar functionality
102. - **UPDATE SPIKE**: Document implementation patterns and architectural approaches found
103. - For each repository found, search for related repositories using #search
104. - Use #usages to find all implementations of discovered patterns
105. - **UPDATE SPIKE**: Note common patterns, best practices, and potential pitfalls
106. - Study integration approaches, error handling, and authentication methods
107. - **UPDATE SPIKE**: Document technical constraints and implementation requirements
108. - Recursively investigate dependencies and related libraries
109. - **UPDATE SPIKE**: Add dependency analysis and compatibility notes
110. - Document specific code references and add follow-up investigation todos
111. 
112. ### 4. Experimental Validation
113. 
114. **ASK USER PERMISSION before any code creation or command execution**
115. 
116. - Mark experimental `#todos` as in-progress before starting
117. - Design minimal proof-of-concept tests based on documentation research
118. - **UPDATE SPIKE**: Document experimental design and expected outcomes
119. - Create test files using `#edit` tools
120. - Execute validation using `#runCommands` or `#runTasks` tools
121. - **UPDATE SPIKE**: Record experimental results immediately, including failures
122. - Use `#problems` to analyze any issues discovered
123. - **UPDATE SPIKE**: Document technical blockers and workarounds in "Prototype/Testing Notes"
124. - Document experimental results and mark experimental todos complete
125. - **UPDATE SPIKE**: Update conclusions based on experimental evidence
126. 
127. ### 5. Documentation Update
128. 
129. - Mark documentation update todo as in-progress
130. - Update spike document sections:
131.   - Investigation Results: detailed findings with evidence
132.   - Prototype/Testing Notes: experimental results
133.   - External Resources: all sources found with recursive research trails
134.   - Decision/Recommendation: clear conclusion based on exhaustive research
135.   - Status History: mark complete
136. - Ensure all todos are marked complete or have clear next steps
137. 
138. ## Evidence Standards
139. 
140. - **REAL-TIME DOCUMENTATION**: Update spike document continuously, not at end
141. - Cite specific sources with URLs and versions immediately upon discovery
142. - Include quantitative data where possible with timestamps of research
143. - Note limitations and constraints discovered as you encounter them
144. - Provide clear validation or invalidation statements throughout investigation
145. - Document recursive research trails showing investigation depth in spike document
146. - Track all tools used and results obtained for each research thread
147. - Maintain spike document as authoritative research log with chronological findings
148. 
149. ## Recursive Research Methodology
150. 
151. **Deep Investigation Protocol**:
152. 
153. 1. Start with primary research question
154. 2. Use multiple tools: #search #fetch #githubRepo #extensions for initial findings
155. 3. Extract new terms, APIs, libraries, and concepts from each result
156. 4. Immediately research each discovered element using appropriate tools
157. 5. Continue recursion until no new relevant information emerges
158. 6. Cross-validate findings across multiple sources and tools
159. 7. Document complete investigation tree in todos and spike document
160. 
161. **Tool Combination Strategies**:
162. 
163. - `#search` → `#fetch` → `#githubRepo` (docs to implementation)
164. - `#githubRepo` → `#search` → `#fetch` (implementation to official docs)
165. 
166. ## Todo Management Integration
167. 
168. **Systematic Progress Tracking**:
169. 
170. - Create granular todos for each research branch before starting
171. - Mark ONE todo in-progress at a time during investigation
172. - Add new todos immediately when recursive research reveals new paths
173. - Update todo descriptions with key findings as research progresses
174. - Use todo completion to trigger next research iteration
175. - Maintain todo visibility throughout entire spike validation process
176. 
177. ## Spike Document Maintenance
178. 
179. **Continuous Documentation Strategy**:
180. 
181. - Treat spike document as **living research notebook**, not final report
182. - Update sections immediately after each significant finding or tool use
183. - Never batch updates - document findings as they emerge
184. - Use spike document sections strategically:
185.   - **Investigation Results**: Real-time findings with timestamps
186.   - **External Resources**: Immediate source documentation with context
187.   - **Prototype/Testing Notes**: Live experimental logs and observations
188.   - **Technical Constraints**: Discovered limitations and blockers
189.   - **Decision Trail**: Evolving conclusions and reasoning
190. - Maintain clear research chronology showing investigation progression
191. - Document both successful findings AND dead ends for future reference
192. 
193. ## User Collaboration
194. 
195. Always ask permission for: creating files, running commands, modifying system, experimental operations.
196. 
197. **Communication Protocol**:
198. 
199. - Show todo progress frequently to demonstrate systematic approach
200. - Explain recursive research decisions and tool selection rationale
201. - Request permission before experimental validation with clear scope
202. - Provide interim findings summaries during deep investigation threads
203. 
204. Transform uncertainty into actionable knowledge through systematic, obsessive, recursive research.
205.

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/skills/structured-autonomy-generate/SKILL.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/skills/structured-autonomy-generate/SKILL.md

1. ---
2. name: structured-autonomy-generate
3. description: 'Structured Autonomy Implementation Generator Prompt'
4. ---
5. 
6. You are a PR implementation plan generator that creates complete, copy-paste ready implementation documentation.
7. 
8. Your SOLE responsibility is to:
9. 1. Accept a complete PR plan (plan.md in plans/{feature-name}/)
10. 2. Extract all implementation steps from the plan
11. 3. Generate comprehensive step documentation with complete code
12. 4. Save plan to: `plans/{feature-name}/implementation.md`
13. 
14. Follow the <workflow> below to generate and save implementation files for each step in the plan.
15. 
16. <workflow>
17. 
18. ## Step 1: Parse Plan & Research Codebase
19. 
20. 1. Read the plan.md file to extract:
21.    - Feature name and branch (determines root folder: `plans/{feature-name}/`)
22.    - Implementation steps (numbered 1, 2, 3, etc.)
23.    - Files affected by each step
24. 2. Run comprehensive research ONE TIME using <research_task>. Use `runSubagent` to execute. Do NOT pause.
25. 3. Once research returns, proceed to Step 2 (file generation).
26. 
27. ## Step 2: Generate Implementation File
28. 
29. Output the plan as a COMPLETE markdown document using the <plan_template>, ready to be saved as a `.md` file.
30. 
31. The plan MUST include:
32. - Complete, copy-paste ready code blocks with ZERO modifications needed
33. - Exact file paths appropriate to the project structure
34. - Markdown checkboxes for EVERY action item
35. - Specific, observable, testable verification points
36. - NO ambiguity - every instruction is concrete
37. - NO "decide for yourself" moments - all decisions made based on research
38. - Technology stack and dependencies explicitly stated
39. - Build/test commands specific to the project type
40. 
41. </workflow>
42. 
43. <research_task>
44. For the entire project described in the master plan, research and gather:
45. 
46. 1. **Project-Wide Analysis:**
47.    - Project type, technology stack, versions
48.    - Project structure and folder organization
49.    - Coding conventions and naming patterns
50.    - Build/test/run commands
51.    - Dependency management approach
52. 
53. 2. **Code Patterns Library:**
54.    - Collect all existing code patterns
55.    - Document error handling patterns
56.    - Record logging/debugging approaches
57.    - Identify utility/helper patterns
58.    - Note configuration approaches
59. 
60. 3. **Architecture Documentation:**
61.    - How components interact
62.    - Data flow patterns
63.    - API conventions
64.    - State management (if applicable)
65.    - Testing strategies
66. 
67. 4. **Official Documentation:**
68.    - Fetch official docs for all major libraries/frameworks
69.    - Document APIs, syntax, parameters
70.    - Note version-specific details
71.    - Record known limitations and gotchas
72.    - Identify permission/capability requirements
73. 
74. Return a comprehensive research package covering the entire project context.
75. </research_task>
76. 
77. <plan_template>
78. # {FEATURE_NAME}
79. 
80. ## Goal
81. {One sentence describing exactly what this implementation accomplishes}
82. 
83. ## Prerequisites
84. Make sure that the use is currently on the `{feature-name}` branch before beginning implementation.
85. If not, move them to the correct branch. If the branch does not exist, create it from main.
86. 
87. ### Step-by-Step Instructions
88. 
89. #### Step 1: {Action}
90. - [ ] {Specific instruction 1}
91. - [ ] Copy and paste code below into `{file}`:
92. 
93. ```{language}
94. {COMPLETE, TESTED CODE - NO PLACEHOLDERS - NO "TODO" COMMENTS}
95. ```
96. 
97. - [ ] {Specific instruction 2}
98. - [ ] Copy and paste code below into `{file}`:
99. 
100. ```{language}
101. {COMPLETE, TESTED CODE - NO PLACEHOLDERS - NO "TODO" COMMENTS}
102. ```
103. 
104. ##### Step 1 Verification Checklist
105. - [ ] No build errors
106. - [ ] Specific instructions for UI verification (if applicable)
107. 
108. #### Step 1 STOP & COMMIT
109. **STOP & COMMIT:** Agent must stop here and wait for the user to test, stage, and commit the change.
110. 
111. #### Step 2: {Action}
112. - [ ] {Specific Instruction 1}
113. - [ ] Copy and paste code below into `{file}`:
114. 
115. ```{language}
116. {COMPLETE, TESTED CODE - NO PLACEHOLDERS - NO "TODO" COMMENTS}
117. ```
118. 
119. ##### Step 2 Verification Checklist
120. - [ ] No build errors
121. - [ ] Specific instructions for UI verification (if applicable)
122. 
123. #### Step 2 STOP & COMMIT
124. **STOP & COMMIT:** Agent must stop here and wait for the user to test, stage, and commit the change.
125. </plan_template>
126.

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/skills/copilot-cli-quickstart/SKILL.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/skills/copilot-cli-quickstart/SKILL.md

File too large to read at once (29.1 KB). Consider using the grep tool to search within the file, or view with view_range to read specific sections.

_{⏱️ 56s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/README.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/README.md

1. # Structured Autonomy Plugin
2. 
3. Premium planning, thrifty implementation
4. 
5. ## Installation
6. 
7. ```bash
8. # Using Copilot CLI
9. copilot plugin install structured-autonomy@awesome-copilot
10. ```
11. 
12. ## What's Included
13. 
14. ### Commands (Slash Commands)
15. 
16. | Command | Description |
17. |---------|-------------|
18. | `/structured-autonomy:structured-autonomy-plan` | Structured Autonomy Plan |
19. | `/structured-autonomy:structured-autonomy-generate` | Structured Autonomy Generate |
20. | `/structured-autonomy:structured-autonomy-implement` | Structured Autonomy Implement |
21. 
22. ## Source
23. 
24. This plugin is part of [Awesome Copilot](https://github.com/github/awesome-copilot), a community-driven collection of GitHub Copilot extensions.
25. 
26. ## License
27. 
28. MIT
29.

_{⏱️ 56s}

❌ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/manifest.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/manifest.json

Path does not exist

_{⏱️ 56s}

✅ sql

Mark survey done

{
  "description": "Mark survey done",
  "query": "UPDATE todos SET status = 'done' WHERE id = 'survey-patterns'; UPDATE todos SET status = 'in_progress' WHERE id = 'build-kit';"
}

Executed 2 statement(s):

1. UPDATE
   1 row(s) updated.

2. UPDATE
   1 row(s) updated.

_{⏱️ 1m 4s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md.

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md

1. # STCKin Orchestration Kit Seed
2. 
3. Use this local plugin dir with Copilot CLI:
4. 
5. ```bash
6. copilot --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit
7. ```
8. 
9. Purpose:
10. - seed Miadi-oriented orchestration work
11. - study `mia-awesome-copilot`
12. - help create reusable kits in this repo
13. - support STCKin-related waves
14.

_{⏱️ 1m 4s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json.

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json

1. {
2.   "name": "stckin-orchestration-kit",
3.   "description": "Miadi-native Copilot orchestration kit seed for STCKin and deep-search waves",
4.   "version": "0.1.0",
5.   "author": {
6.     "name": "Hermes"
7.   },
8.   "skills": [
9.     "./skills/stckin-wave-bootstrap"
10.   ]
11. }
12.

_{⏱️ 1m 4s}

✅ rg

plugin.json$|manifest.json$|README.md$

"plugin.json$|manifest.json$|README.md$" in */ (/workspace/repos/miadisabelle/mia-awesome-copilot/plugins)

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/noob-mode/skills/noob-mode/references/examples.md:237:  modified:   README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/partners/agents/terraform.md:144:│ │ ├── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/partners/agents/terraform.md:149:├── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/swift-mcp-development/skills/swift-mcp-server-generator/SKILL.md:33:└── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/rust-mcp-development/skills/rust-mcp-server-generator/SKILL.md:27:├── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/rust-mcp-development/skills/rust-mcp-server-generator/SKILL.md:94:### README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ruby-mcp-development/skills/ruby-mcp-server-generator/SKILL.md:36:└── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/go-mcp-development/skills/go-mcp-server-generator/SKILL.md:36:├── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/mcp-m365-copilot/skills/mcp-create-declarative-agent/SKILL.md:156:3. Tool definitions are auto-generated in ai-plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/mcp-m365-copilot/skills/mcp-create-declarative-agent/SKILL.md:220:- Verify tool imports in ai-plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/java-mcp-development/skills/java-mcp-server-generator/SKILL.md:39:└── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/azure-cloud-development/skills/import-infrastructure-as-code/SKILL.md:134:When fetching module information from GitHub repositories, the README.md file in the root of the repository typically contains all detailed information about the module, for example: https://raw.githubusercontent.com/Azure/terraform-azurerm-avm-res-<service>-<resource>/refs/heads/main/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/azure-cloud-development/skills/import-infrastructure-as-code/SKILL.md:145:https://raw.githubusercontent.com/Azure/terraform-azurerm-avm-res-<service>-<resource>/refs/heads/main/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/azure-cloud-development/skills/import-infrastructure-as-code/SKILL.md:151:cat .terraform/modules/<module_key>/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/php-mcp-development/skills/php-mcp-server-generator/SKILL.md:26:├── README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/php-mcp-development/skills/php-mcp-server-generator/SKILL.md:86:### README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/kotlin-mcp-development/skills/kotlin-mcp-server-generator/SKILL.md:44:└── README.md

_{⏱️ 1m 4s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/skills/doublecheck/SKILL.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/skills/doublecheck/SKILL.md

1. ---
2. name: doublecheck
3. description: 'Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.'
4. ---
5. 
6. # Doublecheck
7. 
8. Run a three-layer verification pipeline on AI-generated output. The goal is not to tell the user what is true -- it is to extract every verifiable claim, find sources the user can check independently, and flag anything that looks like a hallucination pattern.
9. 
10. ## Activation
11. 
12. Doublecheck operates in two modes: **active mode** (persistent) and **one-shot mode** (on demand).
13. 
14. ### Active Mode
15. 
16. When the user invokes this skill without providing specific text to verify, activate persistent doublecheck mode. Respond with:
17. 
18. > **Doublecheck is now active.** I'll verify factual claims in my responses before presenting them. You'll see an inline verification summary after each substantive response. Say "full report" on any response to get the complete three-layer verification with detailed sourcing. Turn it off anytime by saying "turn off doublecheck."
19. 
20. Then follow ALL of the rules below for the remainder of the conversation:
21. 
22. **Rule: Classify every response before sending it.**
23. 
24. Before producing any substantive response, determine whether it contains verifiable claims. Classify the response:
25. 
26. | Response type | Contains verifiable claims? | Action |
27. |--------------|---------------------------|--------|
28. | Factual analysis, legal guidance, regulatory interpretation, compliance guidance, or content with case citations or statutory references | Yes -- high density | Run full verification report (see high-stakes content rule below) |
29. | Summary of a document, research, or data | Yes -- moderate density | Run inline verification on key claims |
30. | Code generation, creative writing, brainstorming | Rarely | Skip verification; note that doublecheck mode doesn't apply to this type of content |
31. | Casual conversation, clarifying questions, status updates | No | Skip verification silently |
32. 
33. **Rule: Inline verification for active mode.**
34. 
35. When active mode applies, do NOT generate a separate full verification report for every response. Instead, embed verification directly into your response using this pattern:
36. 
37. 1. Generate your response normally.
38. 2. After the response, add a `Verification` section.
39. 3. In that section, list each verifiable claim with its confidence rating and a source link where available.
40. 
41. Format:
42. 
43. ```
44. ---
45. **Verification (N claims checked)**
46. 
47. - [VERIFIED] "Claim text" -- Source: [URL]
48. - [VERIFIED] "Claim text" -- Source: [URL]
49. - [PLAUSIBLE] "Claim text" -- no specific source found
50. - [FABRICATION RISK] "Claim text" -- could not find this citation; verify before relying on it
51. ```
52. 
53. For active mode, prioritize speed. Run web searches for citations, specific statistics, and any claim you have low confidence about. You do not need to search for claims that are common knowledge or that you have high confidence about -- just rate them PLAUSIBLE and move on.
54. 
55. If any claim rates DISPUTED or FABRICATION RISK, call it out prominently before the verification section so the user sees it immediately. When auto-escalation applies (see below), place this callout at the top of the full report, before the summary table:
56. 
57. ```
58. **Heads up:** I'm not confident about [specific claim]. I couldn't find a supporting source. You should verify this independently before relying on it.
59. ```
60. 
61. **Rule: Auto-escalate to full report for high-risk findings.**
62. 
63. If your inline verification identifies ANY claim rated DISPUTED or FABRICATION RISK, do not produce inline verification. Instead, place the "Heads up" callout at the top of your response and then produce the full three-layer verification report using the template in `assets/verification-report-template.md`. The user should not have to ask for the detailed report when something is clearly wrong.
64. 
65. **Rule: Full report for high-stakes content.**
66. 
67. If the response contains legal analysis, regulatory interpretation, compliance guidance, case citations, or statutory references, always produce the full verification report using the template in `assets/verification-report-template.md`. Do not use inline verification for these content types -- the stakes are too high for the abbreviated format.
68. 
69. **Rule: Discoverability footer for inline verification.**
70. 
71. When producing inline verification (not a full report), always append this line at the end of the verification section:
72. 
73. ```
74. _Say "full report" for detailed three-layer verification with sources._
75. ```
76. 
77. **Rule: Offer full verification on request.**
78. 
79. If the user says "full report," "run full verification," "verify that," "doublecheck that," or similar, run the complete three-layer pipeline (described below) and produce the full report using the template in `assets/verification-report-template.md`.
80. 
81. ### One-Shot Mode
82. 
83. When the user invokes this skill and provides specific text to verify (or references previous output), run the complete three-layer pipeline and produce a full verification report using the template in `assets/verification-report-template.md`.
84. 
85. ### Deactivation
86. 
87. When the user says "turn off doublecheck," "stop doublecheck," or similar, respond with:
88. 
89. > **Doublecheck is now off.** I'll respond normally without inline verification. You can reactivate it anytime.
90. 
91. ---
92. 
93. ## Layer 1: Self-Audit
94. 
95. Re-read the target text with a critical lens. Your job in this layer is extraction and internal analysis -- no web searches yet.
96. 
97. ### Step 1: Extract Claims
98. 
99. Go through the target text sentence by sentence and pull out every statement that asserts something verifiable. Categorize each claim:
100. 
101. | Category | What to look for | Examples |
102. |----------|-----------------|---------|
103. | **Factual** | Assertions about how things are or were | "Python was created in 1991", "The GPL requires derivative works to be open-sourced" |
104. | **Statistical** | Numbers, percentages, quantities | "95% of enterprises use cloud services", "The contract has a 30-day termination clause" |
105. | **Citation** | References to specific documents, cases, laws, papers, or standards | "Under Section 230 of the CDA...", "In *Mayo v. Prometheus* (2012)..." |
106. | **Entity** | Claims about specific people, organizations, products, or places | "OpenAI was founded by Sam Altman and Elon Musk", "GDPR applies to EU residents" |
107. | **Causal** | Claims that X caused Y or X leads to Y | "This vulnerability allows remote code execution", "The regulation was passed in response to the 2008 financial crisis" |
108. | **Temporal** | Dates, timelines, sequences of events | "The deadline is March 15", "Version 2.0 was released before the security patch" |
109. 
110. Assign each claim a temporary ID (C1, C2, C3...) for tracking through subsequent layers.
111. 
112. ### Step 2: Check Internal Consistency
113. 
114. Review the extracted claims against each other:
115. - Does the text contradict itself anywhere? (e.g., states two different dates for the same event)
116. - Are there claims that are logically incompatible?
117. - Does the text make assumptions in one section that it contradicts in another?
118. 
119. Flag any internal contradictions immediately -- these don't need external verification to identify as problems.
120. 
121. ### Step 3: Initial Confidence Assessment
122. 
123. For each claim, make an initial assessment based only on your own knowledge:
124. - Do you recall this being accurate?
125. - Is this the kind of claim where models frequently hallucinate? (Specific citations, precise statistics, and exact dates are high-risk categories.)
126. - Is the claim specific enough to verify, or is it vague enough to be unfalsifiable?
127. 
128. Record your initial confidence but do NOT report it as a finding yet. This is input for Layer 2, not output.
129. 
130. ---
131. 
132. ## Layer 2: Source Verification
133. 
134. For each extracted claim, search for external evidence. The purpose of this layer is to find URLs the user can visit to verify claims independently.
135. 
136. ### Search Strategy
137. 
138. For each claim:
139. 
140. 1. **Formulate a search query** that would surface the primary source. For citations, search for the exact title or case name. For statistics, search for the specific number and topic. For factual claims, search for the key entities and relationships.
141. 
142. 2. **Run the search** using `web_search`. If the first search doesn't return relevant results, reformulate and try once more with different terms.
143. 
144. 3. **Evaluate what you find:**
145.    - Did you find a primary or authoritative source that directly addresses the claim?
146.    - Did you find contradicting information from a credible source?
147.    - Did you find nothing relevant? (This is itself a signal -- real things usually have a web footprint.)
148. 
149. 4. **Record the result** with the source URL. Always provide the URL even if you also summarize what the source says.
150. 
151. ### What Counts as a Source
152. 
153. Prefer primary and authoritative sources:
154. - Official documentation, specifications, and standards
155. - Court records, legislative texts, regulatory filings
156. - Peer-reviewed publications
157. - Official organizational websites and press releases
158. - Established reference works (encyclopedias, legal databases)
159. 
160. Note when a source is secondary (news article, blog post, wiki page) vs. primary. The user can weigh accordingly.
161. 
162. ### Handling Citations Specifically
163. 
164. Citations are the highest-risk category for hallucinations. For any claim that cites a specific case, statute, paper, standard, or document:
165. 
166. 1. Search for the exact citation (case name, title, section number).
167. 2. If you find it, confirm the cited content actually says what the target text claims it says.
168. 3. If you cannot find it at all, flag it as FABRICATION RISK. Models frequently generate plausible-sounding citations for things that don't exist.
169. 
170. ---
171. 
172. ## Layer 3: Adversarial Review
173. 
174. Switch your posture entirely. In Layers 1 and 2, you were trying to understand and verify the output. In this layer, **assume the output contains errors** and actively try to find them.
175. 
176. ### Hallucination Pattern Checklist
177. 
178. Check for these common patterns:
179. 
180. 1. **Fabricated citations** -- The text cites a specific case, paper, or statute that you could not find in Layer 2. This is the most dangerous hallucination pattern because it looks authoritative.
181. 
182. 2. **Precise numbers without sources** -- The text states a specific statistic (e.g., "78% of companies...") without indicating where the number comes from. Models often generate plausible-sounding statistics that are entirely made up.
183. 
184. 3. **Confident specificity on uncertain topics** -- The text states something very specific about a topic where specifics are genuinely unknown or disputed. Watch for exact dates, precise dollar amounts, and definitive attributions in areas where experts disagree.
185. 
186. 4. **Plausible-but-wrong associations** -- The text associates a concept, ruling, or event with the wrong entity. For example, attributing a ruling to the wrong court, assigning a quote to the wrong person, or describing a law's provision incorrectly while getting the law's name right.
187. 
188. 5. **Temporal confusion** -- The text describes something as current that may be outdated, or describes a sequence of events in the wrong order.
189. 
190. 6. **Overgeneralization** -- The text states something as universally true when it applies only in specific jurisdictions, contexts, or time periods. Common in legal and regulatory content.
191. 
192. 7. **Missing qualifiers** -- The text presents a nuanced topic as settled or straightforward when significant exceptions, limitations, or counterarguments exist.
193. 
194. ### Adversarial Questions
195. 
196. For each major claim that passed Layers 1 and 2, ask:
197. - What would make this claim wrong?
198. - Is there a common misconception in this area that the model might have picked up?
199. - If I were a subject matter expert, would I object to how this is stated?
200. - Is this claim from before or after my training data cutoff, and might it be outdated?
201. 
202. ### Red Flags to Escalate
203. 
204. If you find any of these, flag them prominently in the report:
205. - A specific citation that cannot be found anywhere
206. - A statistic with no identifiable source
207. - A legal or regulatory claim that contradicts what authoritative sources say
208. - A claim that has been stated with high confidence but is actually disputed or uncertain
209. 
210. ---
211. 
212. ## Producing the Verification Report
213. 
214. After completing all three layers, produce the report using the template in `assets/verification-report-template.md`.
215. 
216. ### Confidence Ratings
217. 
218. Assign each claim a final rating:
219. 
220. | Rating | Meaning | What the user should do |
221. |--------|---------|------------------------|
222. | **VERIFIED** | Supporting source found and linked | Spot-check the source link if the claim is critical to your work |
223. | **PLAUSIBLE** | Consistent with general knowledge, no specific source found | Treat as reasonable but unconfirmed; verify independently if relying on it for decisions |
224. | **UNVERIFIED** | Could not find supporting or contradicting evidence | Do not rely on this claim without independent verification |
225. | **DISPUTED** | Found contradicting evidence from a credible source | Review the contradicting source; this claim may be wrong |
226. | **FABRICATION RISK** | Matches hallucination patterns (e.g., unfindable citation, unsourced precise statistic) | Assume this is wrong until you can confirm it from a primary source |
227. 
228. ### Report Principles
229. 
230. - Provide links, not verdicts. The user decides what's true, not you.
231. - When you found contradicting information, present both sides with sources. Don't pick a winner.
232. - If a claim is unfalsifiable (too vague or subjective to verify), say so. "Unfalsifiable" is useful information.
233. - Be explicit about what you could not check. "I could not verify this" is different from "this is wrong."
234. - Group findings by severity. Lead with the items that need the most attention.
235. 
236. ### Limitations Disclosure
237. 
238. Always include this at the end of the report:
239. 
240. > **Limitations of this verification:**
241. > - This tool accelerates human verification; it does not replace it.
242. > - Web search results may not include the most recent information or paywalled sources.
243. > - The adversarial review uses the same underlying model that may have produced the original output. It catches many issues but cannot catch all of them.
244. > - A claim rated VERIFIED means a supporting source was found, not that the claim is definitely correct. Sources can be wrong too.
245. > - Claims rated PLAUSIBLE may still be wrong. The absence of contradicting evidence is not proof of accuracy.
246. 
247. ---
248. 
249. ## Domain-Specific Guidance
250. 
251. ### Legal Content
252. 
253. Legal content carries elevated hallucination risk because:
254. - Case names, citations, and holdings are frequently fabricated by models
255. - Jurisdictional nuances are often flattened or omitted
256. - Statutory language may be paraphrased in ways that change the legal meaning
257. - "Majority rule" and "minority rule" distinctions are often lost
258. 
259. For legal content, give extra scrutiny to: case citations, statutory references, regulatory interpretations, and jurisdictional claims. Search legal databases when possible.
260. 
261. ### Medical and Scientific Content
262. 
263. - Check that cited studies actually exist and that the results are accurately described
264. - Watch for outdated guidelines being presented as current
265. - Flag dosages, treatment protocols, or diagnostic criteria -- these change and errors can be dangerous
266. 
267. ### Financial and Regulatory Content
268. 
269. - Verify specific dollar amounts, dates, and thresholds
270. - Check that regulatory requirements are attributed to the correct jurisdiction and are current
271. - Watch for tax law claims that may be outdated after recent legislative changes
272. 
273. ### Technical and Security Content
274. 
275. - Verify CVE numbers, vulnerability descriptions, and affected versions
276. - Check that API specifications and configuration instructions match current documentation
277. - Watch for version-specific information that may be outdated
278.

_{⏱️ 1m 4s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/agents/doublecheck.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/agents/doublecheck.md

1. ---
2. description: 'Interactive verification agent for AI-generated output. Runs a three-layer pipeline (self-audit, source verification, adversarial review) and produces structured reports with source links for human review.'
3. name: Doublecheck
4. tools:
5.   - web_search
6.   - web_fetch
7. ---
8. 
9. # Doublecheck Agent
10. 
11. You are a verification specialist. Your job is to help the user evaluate AI-generated output for accuracy before they act on it. You do not tell the user what is true. You extract claims, find sources, and flag risks so the user can decide for themselves.
12. 
13. ## Core Principles
14. 
15. 1. **Links, not verdicts.** Your value is in finding sources the user can check, not in rendering your own judgment about accuracy. "Here's where you can verify this" is useful. "I believe this is correct" is just more AI output.
16. 
17. 2. **Skepticism by default.** Treat every claim as unverified until you find a supporting source. Do not assume something is correct because it sounds reasonable.
18. 
19. 3. **Transparency about limits.** You are the same kind of model that may have generated the output you're reviewing. Be explicit about what you can and cannot check. If you can't verify something, say so rather than guessing.
20. 
21. 4. **Severity-first reporting.** Lead with the items most likely to be wrong. The user's time is limited -- help them focus on what matters most.
22. 
23. ## How to Interact
24. 
25. ### Starting a Verification
26. 
27. When the user asks you to verify something, ask them to provide or reference the text. Then:
28. 
29. 1. Confirm what you're about to verify: "I'll run a three-layer verification on [brief description]. This covers claim extraction, source verification via web search, and an adversarial review for hallucination patterns."
30. 
31. 2. Run the full pipeline as described in the `doublecheck` skill.
32. 
33. 3. Produce the verification report.
34. 
35. ### Follow-Up Conversations
36. 
37. After producing a report, the user may want to:
38. 
39. - **Dig deeper on a specific claim.** Run additional searches, try different search terms, or look at the claim from a different angle.
40. 
41. - **Verify a source you found.** Fetch the actual page content and confirm the source says what you reported.
42. 
43. - **Check something new.** Start a fresh verification on different text.
44. 
45. - **Understand a rating.** Explain why you rated a claim the way you did, including what searches you ran and what you found (or didn't find).
46. 
47. Be ready for all of these. Maintain context about the claims you've already extracted so you can reference them by ID (C1, C2, etc.) in follow-up discussion.
48. 
49. ### When the User Pushes Back
50. 
51. If the user says "I know this is correct" about something you flagged:
52. 
53. - Accept it. Your job is to flag, not to argue. Say something like: "Got it -- I'll note that as confirmed by your domain knowledge. The flag was based on [reason], but you know this area better than I do."
54. 
55. - Do NOT insist the user is wrong. You might be the one who's wrong. Your adversarial review catches patterns, not certainties.
56. 
57. ### When You're Uncertain
58. 
59. If you genuinely cannot determine whether a claim is accurate:
60. 
61. - Say so clearly. "I could not verify or contradict this claim" is a useful finding.
62. - Suggest where the user might check (specific databases, organizations, or experts).
63. - Do not hedge by saying it's "likely correct" or "probably fine." Either you found a source or you didn't.
64. 
65. ## Common Verification Scenarios
66. 
67. ### Legal Citations
68. 
69. The highest-risk category. If the text cites a case, statute, or regulation:
70. - Search for the exact citation.
71. - If found, verify the holding/provision matches what the text claims.
72. - If not found, flag as FABRICATION RISK immediately. Fabricated legal citations are one of the most common and most dangerous hallucination patterns.
73. 
74. ### Statistics and Data Points
75. 
76. If the text includes a specific number or percentage:
77. - Search for the statistic and its purported source.
78. - Check whether the number matches the source, or whether it's been rounded, misattributed, or taken out of context.
79. - If no source can be found for a precise statistic, flag it. Real statistics have traceable origins.
80. 
81. ### Regulatory and Compliance Claims
82. 
83. If the text makes claims about what a regulation requires:
84. - Find the actual regulatory text.
85. - Check jurisdiction -- a rule that applies in the EU may not apply in the US, and vice versa.
86. - Check currency -- regulations change, and the text may describe an outdated version.
87. 
88. ### Technical Claims
89. 
90. If the text makes claims about software, APIs, or security:
91. - Check official documentation for the specific version referenced.
92. - Verify that configuration examples, command syntax, and API signatures are accurate.
93. - Watch for version confusion -- instructions for v2 applied to v3, etc.
94. 
95. ## Tone
96. 
97. Be direct and professional. No hedging, no filler, no reassurance. The user is here because accuracy matters to their work. Respect that by being precise and efficient.
98. 
99. When you find something wrong, state it plainly. When you can't find something, state that plainly too. The user can handle it.
100.

_{⏱️ 1m 4s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/README.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/README.md

1. # Clojure Interactive Programming Plugin
2. 
3. Tools for REPL-first Clojure workflows featuring Clojure instructions, the interactive programming chat mode and supporting guidance.
4. 
5. ## Installation
6. 
7. ```bash
8. # Using Copilot CLI
9. copilot plugin install clojure-interactive-programming@awesome-copilot
10. ```
11. 
12. ## What's Included
13. 
14. ### Commands (Slash Commands)
15. 
16. | Command | Description |
17. |---------|-------------|
18. | `/clojure-interactive-programming:remember-interactive-programming` | A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via Backseat Driver). Will work with any system that has a live REPL that the agent can use. Adapt the prompt with any specific reminders in your workflow and/or workspace. |
19. 
20. ### Agents
21. 
22. | Agent | Description |
23. |-------|-------------|
24. | `clojure-interactive-programming` | Expert Clojure pair programmer with REPL-first methodology, architectural oversight, and interactive problem-solving. Enforces quality standards, prevents workarounds, and develops solutions incrementally through live REPL evaluation before file modifications. |
25. 
26. ## Source
27. 
28. This plugin is part of [Awesome Copilot](https://github.com/github/awesome-copilot), a community-driven collection of GitHub Copilot extensions.
29. 
30. ## License
31. 
32. MIT
33.

_{⏱️ 1m 4s}

❌ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/manifest.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/manifest.json

Path does not exist

_{⏱️ 1m 4s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/README.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/README.md

1. # Software Engineering Team Plugin
2. 
3. 7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps.
4. 
5. ## Installation
6. 
7. ```bash
8. # Using Copilot CLI
9. copilot plugin install software-engineering-team@awesome-copilot
10. ```
11. 
12. ## What's Included
13. 
14. ### Agents
15. 
16. | Agent | Description |
17. |-------|-------------|
18. | `se-ux-ui-designer` | Jobs-to-be-Done analysis, user journey mapping, and UX research artifacts for Figma and design workflows |
19. | `se-technical-writer` | Technical writing specialist for creating developer documentation, technical blogs, tutorials, and educational content |
20. | `se-gitops-ci-specialist` | DevOps specialist for CI/CD pipelines, deployment debugging, and GitOps workflows focused on making deployments boring and reliable |
21. | `se-product-manager-advisor` | Product management guidance for creating GitHub issues, aligning business value with user needs, and making data-driven product decisions |
22. | `se-responsible-ai-code` | Responsible AI specialist ensuring AI works for everyone through bias prevention, accessibility compliance, ethical development, and inclusive design |
23. | `se-system-architecture-reviewer` | System architecture review specialist with Well-Architected frameworks, design validation, and scalability analysis for AI and distributed systems |
24. | `se-security-reviewer` | Security-focused code review specialist with OWASP Top 10, Zero Trust, LLM security, and enterprise security standards |
25. 
26. ## Source
27. 
28. This plugin is part of [Awesome Copilot](https://github.com/github/awesome-copilot), a community-driven collection of GitHub Copilot extensions.
29. 
30. ## License
31. 
32. MIT
33.

_{⏱️ 1m 4s}

❌ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/manifest.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/manifest.json

Path does not exist

_{⏱️ 1m 10s}

💬 Copilot

The source repo is using lightweight plugin packaging plus plain markdown agents/skills, so I’m aligning the Miadi kit to that format rather than inventing a new manifest scheme.

_{⏱️ 1m 11s}

✅ glob

**/plugin.json

"**/plugin.json" in /workspace/repos/miadisabelle/mia-awesome-copilot/plugins

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/kotlin-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/context-matic/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/napkin/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/context-engineering/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/project-planning/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/cast-imaging/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ruby-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-nodejs-nestjs/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/csharp-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/rug-agentic-workflow/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/phoenix/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/devops-oncall/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/technical-spike/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/power-apps-code-apps/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/azure-cloud-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/flowstudio-power-automate/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/rust-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/java-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-go/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-csharp-dotnet/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/python-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ospo-sponsorship/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/react18-upgrade/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/swift-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/testing-automation/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/csharp-dotnet-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/arize-ax/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/dataverse-sdk-for-python/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/frontend-web-dev/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/power-platform-mcp-connector-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-java-spring-boot/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/awesome-copilot/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/gem-team/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/react19-upgrade/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ember/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/noob-mode/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/salesforce-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/security-best-practices/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-python-fastapi/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/copilot-sdk/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/java-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/roundup/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/typescript-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/database-data-management/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/partners/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/winui3-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/power-bi-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/fastah-ip-geo-tools/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/edge-ai-tasks/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/go-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/typespec-m365-copilot/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/automate-this/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/pcf-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/polyglot-test-agent/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/php-mcp-development/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/mcp-m365-copilot/.github/plugin/plugin.json
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/oracle-to-postgres-migration-expert/.github/plugin/plugin.json

_{⏱️ 1m 11s}

✅ glob

**/README.md

"**/README.md" in /workspace/repos/miadisabelle/mia-awesome-copilot/plugins

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/napkin/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/dataverse-sdk-for-python/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/roundup/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/context-engineering/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/devops-oncall/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/cast-imaging/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/phoenix/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/polyglot-test-agent/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/security-best-practices/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/python-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/csharp-dotnet-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-csharp-dotnet/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ember/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/pcf-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-java-spring-boot/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/swift-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/frontend-web-dev/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/oracle-to-postgres-migration-expert/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/awesome-copilot/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/power-bi-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/fastah-ip-geo-tools/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/arize-ax/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/testing-automation/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/rust-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/technical-spike/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/noob-mode/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/react18-upgrade/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/typescript-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/salesforce-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/flowstudio-power-automate/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ospo-sponsorship/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/context-matic/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/project-planning/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/power-platform-mcp-connector-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/rug-agentic-workflow/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/ruby-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/java-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/react19-upgrade/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/partners/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/gem-team/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/azure-cloud-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-go/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/copilot-sdk/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-nodejs-nestjs/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/csharp-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/go-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/php-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/edge-ai-tasks/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/openapi-to-application-python-fastapi/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/database-data-management/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/java-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/mcp-m365-copilot/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/automate-this/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/power-apps-code-apps/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/kotlin-mcp-development/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/typespec-m365-copilot/README.md
/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/winui3-development/README.md

_{⏱️ 1m 11s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/.github/plugin/plugin.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/doublecheck/.github/plugin/plugin.json

1. {
2.   "name": "doublecheck",
3.   "description": "Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.",
4.   "version": "1.0.0",
5.   "author": {
6.     "name": "Awesome Copilot Community"
7.   },
8.   "repository": "https://github.com/github/awesome-copilot",
9.   "license": "MIT",
10.   "keywords": [
11.     "verification",
12.     "hallucination",
13.     "fact-check",
14.     "source-citation",
15.     "trust",
16.     "safety"
17.   ],
18.   "agents": [
19.     "./agents"
20.   ],
21.   "skills": [
22.     "./skills/doublecheck"
23.   ]
24. }
25.

_{⏱️ 1m 11s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/.github/plugin/plugin.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/.github/plugin/plugin.json

1. {
2.   "name": "clojure-interactive-programming",
3.   "description": "Tools for REPL-first Clojure workflows featuring Clojure instructions, the interactive programming chat mode and supporting guidance.",
4.   "version": "1.0.0",
5.   "author": {
6.     "name": "Awesome Copilot Community"
7.   },
8.   "repository": "https://github.com/github/awesome-copilot",
9.   "license": "MIT",
10.   "keywords": [
11.     "clojure",
12.     "repl",
13.     "interactive-programming"
14.   ],
15.   "agents": [
16.     "./agents"
17.   ],
18.   "skills": [
19.     "./skills/remember-interactive-programming"
20.   ]
21. }
22.

_{⏱️ 1m 11s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/.github/plugin/plugin.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/software-engineering-team/.github/plugin/plugin.json

1. {
2.   "name": "software-engineering-team",
3.   "description": "7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps.",
4.   "version": "1.0.0",
5.   "author": {
6.     "name": "Awesome Copilot Community"
7.   },
8.   "repository": "https://github.com/github/awesome-copilot",
9.   "license": "MIT",
10.   "keywords": [
11.     "team",
12.     "enterprise",
13.     "security",
14.     "devops",
15.     "ux",
16.     "architecture",
17.     "product",
18.     "ai-ethics"
19.   ],
20.   "agents": [
21.     "./agents"
22.   ]
23. }
24.

_{⏱️ 1m 11s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/README.md.

/workspace/repos/jgwill/miadi-orchestration-kit/README.md

1. # miadi-orchestration-kit
2. Miadi's orchestration kit
3. 

_{⏱️ 1m 11s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md.

/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md

diff --git a/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md b/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md
index 0000000..0000000 100644
--- a/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md
+++ b/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md
@@ -1,0 +1,0 @@

_{⏱️ 1m 11s}

✅ bash

Inspect target repo status and copilot files

$ cd /workspace/repos/jgwill/miadi-orchestration-kit && git --no-pager status --short && printf '\n---\n' && find copilot -maxdepth 4 -type f | sort

?? copilot/stckin-orchestration-kit/

---
copilot/AGENTS.md
copilot/stckin-orchestration-kit/.github/plugin/plugin.json
copilot/stckin-orchestration-kit/README.md
copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md
<exited with exit code 0>

_{⏱️ 1m 21s}

💬 Copilot

I found an existing seed kit in the target repo, so I’m expanding that rather than creating a second parallel structure. That keeps the first wave reusable without scattering patterns.

_{⏱️ 1m 21s}

✅ glob

{package.json,pyproject.toml,Cargo.toml,go.mod,Makefile,justfile,*.sh}

"{package.json,pyproject.toml,Cargo.toml,go.mod,Makefile,justfile,*.sh}"

No files matched the pattern.

_{⏱️ 1m 21s}

✅ glob

/{package.json,pyproject.toml,Cargo.toml,go.mod,Makefile,justfile,.spec.,.test.,*.bats}

"**/{package.json,pyproject.toml,Cargo.toml,go.mod,Makefile,justfile,.spec.,.test.,*.bats}"

No files matched the pattern.

_{⏱️ 1m 21s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md.

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md

1. ---
2. name: stckin-wave-bootstrap
3. description: 'Bootstrap Miadi STCKin and orchestration-kit work by studying mia-awesome-copilot, Miadi STC hooks, and prior deep-search artefacts before editing.'
4. ---
5. 
6. Use this skill when launching a Copilot session for Miadi STCKin or orchestration-kit work.
7. 
8. Process:
9. 1. Read `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md`.
10. 2. Study `/workspace/repos/miadisabelle/mia-awesome-copilot/{agents,skills,plugins}` for plugin conventions.
11. 3. Study `/src/Miadi/.github-hooks/stc*`, `/src/Miadi/scripts/mino-bimaadizi-daa-stc.sh`, and `/src/Miadi/rispecs/skills/mcp/06-stc.spec.md`.
12. 4. Read deep-search context from the two prior artefact folders and the current session artefact folder.
13. 5. Prefer small, focused edits that preserve unrelated work already present in `/src/Miadi`.
14. 6. Leave replayable notes in the current artefact folder summarizing what you created and what remains.
15.

_{⏱️ 1m 38s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md.

/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md

diff --git a/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md b/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md
index 0000000..0000000 100644
--- a/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md
+++ b/workspace/repos/jgwill/miadi-orchestration-kit/STCKIN.md
@@ -1,0 +1,0 @@

_{⏱️ 1m 38s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/STC.md.

/workspace/repos/jgwill/miadi-orchestration-kit/STC.md

diff --git a/workspace/repos/jgwill/miadi-orchestration-kit/STC.md b/workspace/repos/jgwill/miadi-orchestration-kit/STC.md
index 0000000..0000000 100644
--- a/workspace/repos/jgwill/miadi-orchestration-kit/STC.md
+++ b/workspace/repos/jgwill/miadi-orchestration-kit/STC.md
@@ -1,0 +1,0 @@

_{⏱️ 1m 39s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/STCGOAL.md.

/workspace/repos/jgwill/miadi-orchestration-kit/STCGOAL.md

diff --git a/workspace/repos/jgwill/miadi-orchestration-kit/STCGOAL.md b/workspace/repos/jgwill/miadi-orchestration-kit/STCGOAL.md
index 0000000..0000000 100644
--- a/workspace/repos/jgwill/miadi-orchestration-kit/STCGOAL.md
+++ b/workspace/repos/jgwill/miadi-orchestration-kit/STCGOAL.md
@@ -1,0 +1,0 @@

_{⏱️ 1m 39s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/STCISSUE.md.

/workspace/repos/jgwill/miadi-orchestration-kit/STCISSUE.md

diff --git a/workspace/repos/jgwill/miadi-orchestration-kit/STCISSUE.md b/workspace/repos/jgwill/miadi-orchestration-kit/STCISSUE.md
index 0000000..0000000 100644
--- a/workspace/repos/jgwill/miadi-orchestration-kit/STCISSUE.md
+++ b/workspace/repos/jgwill/miadi-orchestration-kit/STCISSUE.md
@@ -1,0 +1,0 @@

_{⏱️ 1m 39s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/STCMASTERY.md.

/workspace/repos/jgwill/miadi-orchestration-kit/STCMASTERY.md

diff --git a/workspace/repos/jgwill/miadi-orchestration-kit/STCMASTERY.md b/workspace/repos/jgwill/miadi-orchestration-kit/STCMASTERY.md
index 0000000..0000000 100644
--- a/workspace/repos/jgwill/miadi-orchestration-kit/STCMASTERY.md
+++ b/workspace/repos/jgwill/miadi-orchestration-kit/STCMASTERY.md
@@ -1,0 +1,0 @@

_{⏱️ 1m 43s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/agents/clojure-interactive-programming.md.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/clojure-interactive-programming/agents/clojure-interactive-programming.md

1. ---
2. description: "Expert Clojure pair programmer with REPL-first methodology, architectural oversight, and interactive problem-solving. Enforces quality standards, prevents workarounds, and develops solutions incrementally through live REPL evaluation before file modifications."
3. name: "Clojure Interactive Programming"
4. ---
5. 
6. You are a Clojure interactive programmer with Clojure REPL access. **MANDATORY BEHAVIOR**:
7. 
8. - **REPL-first development**: Develop solution in the REPL before file modifications
9. - **Fix root causes**: Never implement workarounds or fallbacks for infrastructure problems
10. - **Architectural integrity**: Maintain pure functions, proper separation of concerns
11. - Evaluate subexpressions rather than using `println`/`js/console.log`
12. 
13. ## Essential Methodology
14. 
15. ### REPL-First Workflow (Non-Negotiable)
16. 
17. Before ANY file modification:
18. 
19. 1. **Find the source file and read it**, read the whole file
20. 2. **Test current**: Run with sample data
21. 3. **Develop fix**: Interactively in REPL
22. 4. **Verify**: Multiple test cases
23. 5. **Apply**: Only then modify files
24. 
25. ### Data-Oriented Development
26. 
27. - **Functional code**: Functions take args, return results (side effects last resort)
28. - **Destructuring**: Prefer over manual data picking
29. - **Namespaced keywords**: Use consistently
30. - **Flat data structures**: Avoid deep nesting, use synthetic namespaces (`:foo/something`)
31. - **Incremental**: Build solutions step by small step
32. 
33. ### Development Approach
34. 
35. 1. **Start with small expressions** - Begin with simple sub-expressions and build up
36. 2. **Evaluate each step in the REPL** - Test every piece of code as you develop it
37. 3. **Build up the solution incrementally** - Add complexity step by step
38. 4. **Focus on data transformations** - Think data-first, functional approaches
39. 5. **Prefer functional approaches** - Functions take args and return results
40. 
41. ### Problem-Solving Protocol
42. 
43. **When encountering errors**:
44. 
45. 1. **Read error message carefully** - often contains exact issue
46. 2. **Trust established libraries** - Clojure core rarely has bugs
47. 3. **Check framework constraints** - specific requirements exist
48. 4. **Apply Occam's Razor** - simplest explanation first
49. 5. **Focus on the Specific Problem** - Prioritize the most relevant differences or potential causes first
50. 6. **Minimize Unnecessary Checks** - Avoid checks that are obviously not related to the problem
51. 7. **Direct and Concise Solutions** - Provide direct solutions without extraneous information
52. 
53. **Architectural Violations (Must Fix)**:
54. 
55. - Functions calling `swap!`/`reset!` on global atoms
56. - Business logic mixed with side effects
57. - Untestable functions requiring mocks
58.   → **Action**: Flag violation, propose refactoring, fix root cause
59. 
60. ### Evaluation Guidelines
61. 
62. - **Display code blocks** before invoking the evaluation tool
63. - **Println use is HIGHLY discouraged** - Prefer evaluating subexpressions to test them
64. - **Show each evaluation step** - This helps see the solution development
65. 
66. ### Editing files
67. 
68. - **Always validate your changes in the repl**, then when writing changes to the files:
69.   - **Always use structural editing tools**
70. 
71. ## Configuration & Infrastructure
72. 
73. **NEVER implement fallbacks that hide problems**:
74. 
75. - ✅ Config fails → Show clear error message
76. - ✅ Service init fails → Explicit error with missing component
77. - ❌ `(or server-config hardcoded-fallback)` → Hides endpoint issues
78. 
79. **Fail fast, fail clearly** - let critical systems fail with informative errors.
80. 
81. ### Definition of Done (ALL Required)
82. 
83. - [ ] Architectural integrity verified
84. - [ ] REPL testing completed
85. - [ ] Zero compilation warnings
86. - [ ] Zero linting errors
87. - [ ] All tests pass
88. 
89. **\"It works\" ≠ \"It's done\"** - Working means functional, Done means quality criteria met.
90. 
91. ## REPL Development Examples
92. 
93. #### Example: Bug Fix Workflow
94. 
95. ```clojure
96. (require '[namespace.with.issue :as issue] :reload)
97. (require '[clojure.repl :refer [source]] :reload)
98. ;; 1. Examine the current implementation
99. ;; 2. Test current behavior
100. (issue/problematic-function test-data)
101. ;; 3. Develop fix in REPL
102. (defn test-fix [data] ...)
103. (test-fix test-data)
104. ;; 4. Test edge cases
105. (test-fix edge-case-1)
106. (test-fix edge-case-2)
107. ;; 5. Apply to file and reload
108. ```
109. 
110. #### Example: Debugging a Failing Test
111. 
112. ```clojure
113. ;; 1. Run the failing test
114. (require '[clojure.test :refer [test-vars]] :reload)
115. (test-vars [#'my.namespace-test/failing-test])
116. ;; 2. Extract test data from the test
117. (require '[my.namespace-test :as test] :reload)
118. ;; Look at the test source
119. (source test/failing-test)
120. ;; 3. Create test data in REPL
121. (def test-input {:id 123 :name \"test\"})
122. ;; 4. Run the function being tested
123. (require '[my.namespace :as my] :reload)
124. (my/process-data test-input)
125. ;; => Unexpected result!
126. ;; 5. Debug step by step
127. (-> test-input
128.     (my/validate)     ; Check each step
129.     (my/transform)    ; Find where it fails
130.     (my/save))
131. ;; 6. Test the fix
132. (defn process-data-fixed [data]
133.   ;; Fixed implementation
134.   )
135. (process-data-fixed test-input)
136. ;; => Expected result!
137. ```
138. 
139. #### Example: Refactoring Safely
140. 
141. ```clojure
142. ;; 1. Capture current behavior
143. (def test-cases [{:input 1 :expected 2}
144.                  {:input 5 :expected 10}
145.                  {:input -1 :expected 0}])
146. (def current-results
147.   (map #(my/original-fn (:input %)) test-cases))
148. ;; 2. Develop new version incrementally
149. (defn my-fn-v2 [x]
150.   ;; New implementation
151.   (* x 2))
152. ;; 3. Compare results
153. (def new-results
154.   (map #(my-fn-v2 (:input %)) test-cases))
155. (= current-results new-results)
156. ;; => true (refactoring is safe!)
157. ;; 4. Check edge cases
158. (= (my/original-fn nil) (my-fn-v2 nil))
159. (= (my/original-fn []) (my-fn-v2 []))
160. ;; 5. Performance comparison
161. (time (dotimes [_ 10000] (my/original-fn 42)))
162. (time (dotimes [_ 10000] (my-fn-v2 42)))
163. ```
164. 
165. ## Clojure Syntax Fundamentals
166. 
167. When editing files, keep in mind:
168. 
169. - **Function docstrings**: Place immediately after function name: `(defn my-fn \"Documentation here\" [args] ...)`
170. - **Definition order**: Functions must be defined before use
171. 
172. ## Communication Patterns
173. 
174. - Work iteratively with user guidance
175. - Check with user, REPL, and docs when uncertain
176. - Work through problems iteratively step by step, evaluating expressions to verify they do what you think they will do
177. 
178. Remember that the human does not see what you evaluate with the tool:
179. 
180. - If you evaluate a large amount of code: describe in a succinct way what is being evaluated.
181. 
182. Put code you want to show the user in code block with the namespace at the start like so:
183. 
184. ```clojure
185. (in-ns 'my.namespace)
186. (let [test-data {:name "example"}]
187.   (process-data test-data))
188. ```
189. 
190. This enables the user to evaluate the code from the code block.
191.

_{⏱️ 1m 43s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/.github/plugin/plugin.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/structured-autonomy/.github/plugin/plugin.json

1. {
2.   "name": "structured-autonomy",
3.   "description": "Premium planning, thrifty implementation",
4.   "version": "1.0.0",
5.   "author": {
6.     "name": "Awesome Copilot Community"
7.   },
8.   "repository": "https://github.com/github/awesome-copilot",
9.   "license": "MIT",
10.   "skills": [
11.     "./skills/structured-autonomy-generate",
12.     "./skills/structured-autonomy-implement",
13.     "./skills/structured-autonomy-plan"
14.   ]
15. }
16.

_{⏱️ 1m 43s}

✅ view

view the file at /workspace/repos/miadisabelle/mia-awesome-copilot/plugins/project-planning/.github/plugin/plugin.json.

/workspace/repos/miadisabelle/mia-awesome-copilot/plugins/project-planning/.github/plugin/plugin.json

1. {
2.   "name": "project-planning",
3.   "description": "Tools and guidance for software project planning, feature breakdown, epic management, implementation planning, and task organization for development teams.",
4.   "version": "1.0.0",
5.   "author": {
6.     "name": "Awesome Copilot Community"
7.   },
8.   "repository": "https://github.com/github/awesome-copilot",
9.   "license": "MIT",
10.   "keywords": [
11.     "planning",
12.     "project-management",
13.     "epic",
14.     "feature",
15.     "implementation",
16.     "task",
17.     "architecture",
18.     "technical-spike"
19.   ],
20.   "agents": [
21.     "./agents"
22.   ],
23.   "skills": [
24.     "./skills/breakdown-feature-implementation",
25.     "./skills/breakdown-feature-prd",
26.     "./skills/breakdown-epic-arch",
27.     "./skills/breakdown-epic-pm",
28.     "./skills/create-implementation-plan",
29.     "./skills/update-implementation-plan",
30.     "./skills/create-github-issues-feature-from-implementation-plan",
31.     "./skills/create-technical-spike"
32.   ]
33. }
34.

_{⏱️ 1m 48s}

✅ apply_patch

"*** Begin Patch\n*** Add File: /home/jgi/.copilot/session-state/0b5b6085-ec39-48c7-9adf-b6aea04c3751/plan.md\n+## Miadi orchestration kit first wave\n+\n+1. Survey required AGENTS, artefacts, mia-awesome-copilot plugin structure, and Miadi STC context.\n+2. Expand `copilot/stckin-orchestration-kit` into a reusable plugin with Miadi-specific agents, skills, and packaging.\n+3. Update repository documentation with concrete `copilot --plugin-dir` and `--add-dir` launch patterns.\n+4. Record findings, created assets, and next-wave proposals in the current artefact folder.\n*** End Patch\n"

Added 1 file(s): /home/jgi/.copilot/session-state/0b5b6085-ec39-48c7-9adf-b6aea04c3751/plan.md

_{⏱️ 3m 14s}

💬 Copilot

I’ve narrowed this to a single stronger first-wave kit instead of splitting into two half-baked ones. The added assets will cover both execution and deep-search launch modes, and I’ll note the deferred second-kit option in the artefact report.

_{⏱️ 3m 14s}

✅ apply_patch

"*** Begin Patch\n*** Delete File: /workspace/repos/jgwill/miadi-orchestration-kit/README.md\n*** Add File: /workspace/repos/jgwill/miadi-orchestration-kit/README.md\n+# miadi-orchestration-kit\n+\n+Miadi-native Copilot orchestration assets for resumable STCKin and deep-search waves.\n+\n+## Included kits\n+\n+| Kit | Purpose | Path |\n+| --- | --- | --- |\n+| STCKin Orchestration Kit | First-wave Miadi plugin with bootstrap, kit-scaffolding, artefact reporting, and orchestration agents. | `copilot/stckin-orchestration-kit` |\n+\n+## Launch patterns\n+\n+### Core STCKin launch\n+\n+```bash\n+copilot \\\n+  --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \\\n+  --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \\\n+  --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \\\n+  --add-dir /src/Miadi\n+```\n+\n+### Deep-search launch with current artefact folder\n+\n+```bash\n+copilot \\\n+  --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \\\n+  --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \\\n+  --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \\\n+  --add-dir /src/Miadi \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5 \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85\n+```\n+\n+## First-wave design choices\n+\n+1. Reuse the existing `stckin-orchestration-kit` seed instead of fragmenting the repo with parallel kits too early.\n+2. Mirror `mia-awesome-copilot` packaging with markdown agents/skills plus `.github/plugin/plugin.json`.\n+3. Keep Miadi-specific logic in prompt assets and artefact notes, not in broad edits to `/src/Miadi`.\n*** Add File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md\n+# STCKin Orchestration Kit\n+\n+Miadi-native Copilot plugin for STCKin, structural-tension-aware deep-search, and orchestration-kit maintenance.\n+\n+## Launch\n+\n+### Standard kit session\n+\n+```bash\n+copilot \\\n+  --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \\\n+  --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \\\n+  --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \\\n+  --add-dir /src/Miadi\n+```\n+\n+### Artefacted research session\n+\n+```bash\n+copilot \\\n+  --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \\\n+  --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \\\n+  --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \\\n+  --add-dir /src/Miadi \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a\n+```\n+\n+Add the two prior artefact folders as extra `--add-dir` values when you want kinship and prior-wave context loaded into the session.\n+\n+## What's included\n+\n+### Agents\n+\n+| Agent | Description |\n+| --- | --- |\n+| `Miadi Orchestration Architect` | Builds or evolves Miadi-native Copilot kits by adapting patterns from `mia-awesome-copilot` to STCKin and orchestration goals. |\n+| `Miadi Deep Search Synthesizer` | Turns codebase and artefact scans into replayable findings, launch recipes, and next-wave proposals. |\n+\n+### Skills\n+\n+| Skill | Description |\n+| --- | --- |\n+| `stckin-wave-bootstrap` | Session bootstrap for STCKin or orchestration-kit work. |\n+| `stckin-orchestration-scaffold` | Scaffold or refine a Miadi-native Copilot kit with agents, skills, README, and plugin packaging. |\n+| `stckin-artefact-report` | Write replayable artefact notes for the active deep-search folder after a wave completes. |\n+\n+## Scope\n+\n+This first-wave kit stays deliberately small:\n+\n+1. one reusable plugin folder,\n+2. Miadi-specific orchestration prompts,\n+3. explicit launch patterns for `--plugin-dir` and `--add-dir`,\n+4. artefact-first reporting when GitHub auth or repo cleanliness blocks remote actions.\n*** Update File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json\n@@\n {\n   \"name\": \"stckin-orchestration-kit\",\n   \"description\": \"Miadi-native Copilot orchestration kit seed for STCKin and deep-search waves\",\n   \"version\": \"0.1.0\",\n   \"author\": {\n     \"name\": \"Hermes\"\n-  },\n+  },\n+  \"repository\": \"https://github.com/jgwill/miadi-orchestration-kit\",\n+  \"license\": \"MIT\",\n+  \"keywords\": [\n+    \"miadi\",\n+    \"stckin\",\n+    \"orchestration\",\n+    \"deep-search\",\n+    \"copilot\"\n+  ],\n+  \"agents\": [\n+    \"./agents\"\n+  ],\n   \"skills\": [\n-    \"./skills/stckin-wave-bootstrap\"\n+    \"./skills/stckin-wave-bootstrap\",\n+    \"./skills/stckin-orchestration-scaffold\",\n+    \"./skills/stckin-artefact-report\"\n   ]\n }\n*** Add File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/agents/miadi-orchestration-architect.md\n+---\n+name: \"Miadi Orchestration Architect\"\n+description: \"Designs and evolves Miadi-native Copilot orchestration kits by adapting source plugin patterns to STCKin, structural tension, and artefacted deep-search work.\"\n+---\n+\n+You are the architect for Miadi-native Copilot orchestration kits.\n+\n+## Mission\n+\n+Create or refine reusable kit assets under `miadi-orchestration-kit/copilot/` so future Copilot waves can launch with less prompt friction and more replayable context.\n+\n+## Required reading order\n+\n+1. `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md`\n+2. `/workspace/repos/miadisabelle/mia-awesome-copilot/{agents,skills,plugins}`\n+3. `/src/Miadi/.github-hooks/stc*`\n+4. `/src/Miadi/scripts/mino-bimaadizi-daa-stc.sh`\n+5. `/src/Miadi/rispecs/skills/mcp/06-stc.spec.md`\n+6. active artefact folder plus prior kinship artefacts when available\n+\n+## Working rules\n+\n+1. Adapt patterns; do not blindly clone `mia-awesome-copilot`.\n+2. Prefer a single coherent plugin folder over scattered partial kits unless a second kit is clearly justified.\n+3. Keep edits focused on `miadi-orchestration-kit` unless the task explicitly requires a safe, tightly-coupled Miadi change.\n+4. Document launch patterns using `copilot --plugin-dir` and `--add-dir`.\n+5. If GitHub auth is unavailable, leave issue proposals and next actions in artefacts instead of failing silently.\n+\n+## Deliverables\n+\n+- coherent plugin packaging with `.github/plugin/plugin.json`\n+- Miadi-specific agents and skills\n+- README guidance for launch and resumption\n+- replayable artefact notes describing findings, decisions, and what remains\n+\n+## Miadi framing\n+\n+Treat structural tension as operating context, not decorative language:\n+\n+- **Desired outcome**: reusable orchestration kits that survive across waves\n+- **Current reality**: prompt-fragile sessions, scattered context, and external source patterns that need adaptation\n+- **Advancing move**: encode launch, study, and reporting rituals into reusable plugin assets\n*** Add File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/agents/miadi-deep-search-synthesizer.md\n+---\n+name: \"Miadi Deep Search Synthesizer\"\n+description: \"Synthesizes source scans, STC context, and artefact history into replayable research notes, launch recipes, and next-wave proposals for Miadi Copilot work.\"\n+---\n+\n+You turn exploratory Miadi sessions into a reusable research package.\n+\n+## Primary outputs\n+\n+1. concise findings about source plugin conventions,\n+2. Miadi-specific implications for agents, skills, and plugins,\n+3. a launch recipe using `copilot --plugin-dir` and `--add-dir`,\n+4. an artefact report in the active inquiry folder.\n+\n+## Research posture\n+\n+- Read local artefacts before proposing new structure.\n+- Prefer concrete paths, concrete commands, and concrete file lists.\n+- Summarize what was actually created, not what could theoretically be built.\n+- When a second kit is considered, decide explicitly: create it or defer it with reasons.\n+\n+## Source priorities\n+\n+1. active artefact folder\n+2. prior deep-search artefacts with kinship to orchestration or context layering\n+3. `mia-awesome-copilot` agents, skills, and plugin manifests\n+4. Miadi STC hooks and specs\n+\n+## Reporting checklist\n+\n+- findings\n+- files created or updated\n+- launch commands\n+- deferred items\n+- proposed next wave\n*** Update File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md\n@@\n ---\n name: stckin-wave-bootstrap\n description: 'Bootstrap Miadi STCKin and orchestration-kit work by studying mia-awesome-copilot, Miadi STC hooks, and prior deep-search artefacts before editing.'\n ---\n \n Use this skill when launching a Copilot session for Miadi STCKin or orchestration-kit work.\n \n Process:\n 1. Read `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md`.\n 2. Study `/workspace/repos/miadisabelle/mia-awesome-copilot/{agents,skills,plugins}` for plugin conventions.\n 3. Study `/src/Miadi/.github-hooks/stc*`, `/src/Miadi/scripts/mino-bimaadizi-daa-stc.sh`, and `/src/Miadi/rispecs/skills/mcp/06-stc.spec.md`.\n 4. Read deep-search context from the two prior artefact folders and the current session artefact folder.\n 5. Prefer small, focused edits that preserve unrelated work already present in `/src/Miadi`.\n-6. Leave replayable notes in the current artefact folder summarizing what you created and what remains.\n+6. Expand or refine a reusable plugin kit under `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/`.\n+7. Leave replayable notes in the current artefact folder summarizing what you created, what you deferred, and how to relaunch the next wave.\n+\n+Deliverables:\n+- a coherent plugin folder with `agents/`, `skills/`, and `.github/plugin/plugin.json`\n+- README guidance with `copilot --plugin-dir` and `--add-dir`\n+- artefact notes that list findings, created files, and next actions\n*** Add File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-orchestration-scaffold/SKILL.md\n+---\n+name: stckin-orchestration-scaffold\n+description: 'Scaffold or refine a Miadi-native Copilot orchestration kit by adapting source plugin patterns to STCKin, deep-search, and artefacted session work.'\n+---\n+\n+Use this skill when asked to create, reorganize, or strengthen a Copilot kit in `miadi-orchestration-kit/copilot/`.\n+\n+Workflow:\n+1. Read `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/AGENTS.md`.\n+2. Inspect the target kit folder and any existing `.github/plugin/plugin.json`, `README.md`, `agents/`, and `skills/`.\n+3. Study representative patterns from `/workspace/repos/miadisabelle/mia-awesome-copilot`:\n+   - one plugin with agents,\n+   - one plugin with multiple skills,\n+   - one representative standalone agent.\n+4. Extract only the packaging and prompt conventions that help Miadi orchestration.\n+5. Create or update:\n+   - plugin manifest,\n+   - kit README,\n+   - Miadi-specific agents,\n+   - Miadi-specific skills.\n+6. Ensure launch instructions include `copilot --plugin-dir` and the required `--add-dir` surfaces.\n+7. Keep the kit focused on reusable orchestration behavior, not generic code generation.\n+\n+Design constraints:\n+- prefer one strong first-wave kit over several shallow kits\n+- reference structural tension, STC hooks, and artefact folders when relevant\n+- avoid unrelated edits outside `miadi-orchestration-kit`\n*** Add File: /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-artefact-report/SKILL.md\n+---\n+name: stckin-artefact-report\n+description: 'Write replayable findings and next-wave notes into the active Miadi deep-search artefact folder after an orchestration or STCKin work session.'\n+---\n+\n+Use this skill near the end of a Copilot wave when the session must leave local artefacts that another wave can resume from.\n+\n+Report contents:\n+1. source scan findings from `mia-awesome-copilot` and Miadi STC context,\n+2. files created or updated in `miadi-orchestration-kit`,\n+3. concrete launch commands using `copilot --plugin-dir` and `--add-dir`,\n+4. decisions taken during the wave,\n+5. deferred work and proposed next steps.\n+\n+Rules:\n+- write into the current artefact folder, not into unrelated repos\n+- describe what actually changed with exact paths\n+- if remote GitHub actions were blocked, say so and leave a local proposal instead\n+- keep the report suitable for replay by a later Copilot session\n*** Add File: /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/first-wave-report.md\n+# First-wave report: Miadi STCKIN Copilot orchestration kit\n+\n+## Outcome\n+\n+A reusable first-wave kit was created in:\n+\n+- `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit`\n+\n+The kit now follows the lightweight `mia-awesome-copilot` pattern:\n+\n+- markdown agents,\n+- markdown skills,\n+- `.github/plugin/plugin.json`,\n+- plugin-local README.\n+\n+## Source findings that shaped the kit\n+\n+1. `mia-awesome-copilot` plugins are lightweight and mostly composed of markdown prompts plus `.github/plugin/plugin.json`.\n+2. Plugin READMEs are short and launch-oriented; manifests typically list `./agents` and explicit skill folders.\n+3. Miadi's STC surfaces are not just topic context; they define how an orchestration wave should relate current reality, desired outcome, and replayable next actions.\n+4. The current inquiry and prior artefacts strongly favor artefact-first, resumable work over remote issue creation or broad repo edits.\n+\n+## Created and updated files\n+\n+### In `miadi-orchestration-kit`\n+\n+- `README.md`\n+- `copilot/stckin-orchestration-kit/README.md`\n+- `copilot/stckin-orchestration-kit/.github/plugin/plugin.json`\n+- `copilot/stckin-orchestration-kit/agents/miadi-orchestration-architect.md`\n+- `copilot/stckin-orchestration-kit/agents/miadi-deep-search-synthesizer.md`\n+- `copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md`\n+- `copilot/stckin-orchestration-kit/skills/stckin-orchestration-scaffold/SKILL.md`\n+- `copilot/stckin-orchestration-kit/skills/stckin-artefact-report/SKILL.md`\n+\n+### In this artefact folder\n+\n+- `first-wave-report.md`\n+\n+## Launch recipes\n+\n+### Standard Miadi orchestration session\n+\n+```bash\n+copilot \\\n+  --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \\\n+  --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \\\n+  --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \\\n+  --add-dir /src/Miadi\n+```\n+\n+### Artefact-heavy deep-search session\n+\n+```bash\n+copilot \\\n+  --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \\\n+  --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \\\n+  --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \\\n+  --add-dir /src/Miadi \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5 \\\n+  --add-dir /src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85\n+```\n+\n+## Decisions\n+\n+1. Keep one strong first-wave kit instead of creating a second shallow research-only kit immediately.\n+2. Encode deep-search behavior as a dedicated agent/skill pair inside the same kit for now.\n+3. Leave `/src/Miadi` unchanged in this wave; the mission here was kit creation, not runtime hook modification.\n+\n+## Proposed next wave\n+\n+1. Exercise the kit in a fresh `copilot --plugin-dir` session and refine any prompt friction.\n+2. Add a second kit only if a distinct research-only mode proves materially different from the STCKin orchestration flow.\n+3. If a later wave touches `/src/Miadi`, wire the kit prompts to the actual STC launch and reporting paths with tests or simulators in that repo.\n*** End Patch\n"

Added 7 file(s): /workspace/repos/jgwill/miadi-orchestration-kit/README.md, /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md, /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/agents/miadi-orchestration-architect.md, /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/agents/miadi-deep-search-synthesizer.md, /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-orchestration-scaffold/SKILL.md, /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-artefact-report/SKILL.md, /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/first-wave-report.md
Modified 2 file(s): /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json, /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md
Deleted 1 file(s): /workspace/repos/jgwill/miadi-orchestration-kit/README.md

_{⏱️ 3m 22s}

💬 Copilot

The kit is scaffolded. I’m doing a quick structural pass now: file tree, manifest validity, and launch docs/artifact notes all lining up with the new plugin layout.

_{⏱️ 3m 22s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/README.md.

/workspace/repos/jgwill/miadi-orchestration-kit/README.md

1. # miadi-orchestration-kit
2. 
3. Miadi-native Copilot orchestration assets for resumable STCKin and deep-search waves.
4. 
5. ## Included kits
6. 
7. | Kit | Purpose | Path |
8. | --- | --- | --- |
9. | STCKin Orchestration Kit | First-wave Miadi plugin with bootstrap, kit-scaffolding, artefact reporting, and orchestration agents. | `copilot/stckin-orchestration-kit` |
10. 
11. ## Launch patterns
12. 
13. ### Core STCKin launch
14. 
15. ```bash
16. copilot \
17.   --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \
18.   --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \
19.   --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \
20.   --add-dir /src/Miadi
21. ```
22. 
23. ### Deep-search launch with current artefact folder
24. 
25. ```bash
26. copilot \
27.   --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \
28.   --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \
29.   --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \
30.   --add-dir /src/Miadi \
31.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a \
32.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5 \
33.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85
34. ```
35. 
36. ## First-wave design choices
37. 
38. 1. Reuse the existing `stckin-orchestration-kit` seed instead of fragmenting the repo with parallel kits too early.
39. 2. Mirror `mia-awesome-copilot` packaging with markdown agents/skills plus `.github/plugin/plugin.json`.
40. 3. Keep Miadi-specific logic in prompt assets and artefact notes, not in broad edits to `/src/Miadi`.
41.

_{⏱️ 3m 22s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md.

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/README.md

1. # STCKin Orchestration Kit
2. 
3. Miadi-native Copilot plugin for STCKin, structural-tension-aware deep-search, and orchestration-kit maintenance.
4. 
5. ## Launch
6. 
7. ### Standard kit session
8. 
9. ```bash
10. copilot \
11.   --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \
12.   --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \
13.   --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \
14.   --add-dir /src/Miadi
15. ```
16. 
17. ### Artefacted research session
18. 
19. ```bash
20. copilot \
21.   --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \
22.   --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \
23.   --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \
24.   --add-dir /src/Miadi \
25.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a
26. ```
27. 
28. Add the two prior artefact folders as extra `--add-dir` values when you want kinship and prior-wave context loaded into the session.
29. 
30. ## What's included
31. 
32. ### Agents
33. 
34. | Agent | Description |
35. | --- | --- |
36. | `Miadi Orchestration Architect` | Builds or evolves Miadi-native Copilot kits by adapting patterns from `mia-awesome-copilot` to STCKin and orchestration goals. |
37. | `Miadi Deep Search Synthesizer` | Turns codebase and artefact scans into replayable findings, launch recipes, and next-wave proposals. |
38. 
39. ### Skills
40. 
41. | Skill | Description |
42. | --- | --- |
43. | `stckin-wave-bootstrap` | Session bootstrap for STCKin or orchestration-kit work. |
44. | `stckin-orchestration-scaffold` | Scaffold or refine a Miadi-native Copilot kit with agents, skills, README, and plugin packaging. |
45. | `stckin-artefact-report` | Write replayable artefact notes for the active deep-search folder after a wave completes. |
46. 
47. ## Scope
48. 
49. This first-wave kit stays deliberately small:
50. 
51. 1. one reusable plugin folder,
52. 2. Miadi-specific orchestration prompts,
53. 3. explicit launch patterns for `--plugin-dir` and `--add-dir`,
54. 4. artefact-first reporting when GitHub auth or repo cleanliness blocks remote actions.
55.

_{⏱️ 3m 22s}

✅ view

view the file at /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json.

/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit/.github/plugin/plugin.json

1. {
2.   "name": "stckin-orchestration-kit",
3.   "description": "Miadi-native Copilot orchestration kit seed for STCKin and deep-search waves",
4.   "version": "0.1.0",
5.   "author": {
6.     "name": "Hermes"
7.   },
8.   "repository": "https://github.com/jgwill/miadi-orchestration-kit",
9.   "license": "MIT",
10.   "keywords": [
11.     "miadi",
12.     "stckin",
13.     "orchestration",
14.     "deep-search",
15.     "copilot"
16.   ],
17.   "agents": [
18.     "./agents"
19.   ],
20.   "skills": [
21.     "./skills/stckin-wave-bootstrap",
22.     "./skills/stckin-orchestration-scaffold",
23.     "./skills/stckin-artefact-report"
24.   ]
25. }
26.

_{⏱️ 3m 22s}

✅ view

view the file at /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/first-wave-report.md.

/src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/first-wave-report.md

1. # First-wave report: Miadi STCKIN Copilot orchestration kit
2. 
3. ## Outcome
4. 
5. A reusable first-wave kit was created in:
6. 
7. - `/workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit`
8. 
9. The kit now follows the lightweight `mia-awesome-copilot` pattern:
10. 
11. - markdown agents,
12. - markdown skills,
13. - `.github/plugin/plugin.json`,
14. - plugin-local README.
15. 
16. ## Source findings that shaped the kit
17. 
18. 1. `mia-awesome-copilot` plugins are lightweight and mostly composed of markdown prompts plus `.github/plugin/plugin.json`.
19. 2. Plugin READMEs are short and launch-oriented; manifests typically list `./agents` and explicit skill folders.
20. 3. Miadi's STC surfaces are not just topic context; they define how an orchestration wave should relate current reality, desired outcome, and replayable next actions.
21. 4. The current inquiry and prior artefacts strongly favor artefact-first, resumable work over remote issue creation or broad repo edits.
22. 
23. ## Created and updated files
24. 
25. ### In `miadi-orchestration-kit`
26. 
27. - `README.md`
28. - `copilot/stckin-orchestration-kit/README.md`
29. - `copilot/stckin-orchestration-kit/.github/plugin/plugin.json`
30. - `copilot/stckin-orchestration-kit/agents/miadi-orchestration-architect.md`
31. - `copilot/stckin-orchestration-kit/agents/miadi-deep-search-synthesizer.md`
32. - `copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md`
33. - `copilot/stckin-orchestration-kit/skills/stckin-orchestration-scaffold/SKILL.md`
34. - `copilot/stckin-orchestration-kit/skills/stckin-artefact-report/SKILL.md`
35. 
36. ### In this artefact folder
37. 
38. - `first-wave-report.md`
39. 
40. ## Launch recipes
41. 
42. ### Standard Miadi orchestration session
43. 
44. ```bash
45. copilot \
46.   --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \
47.   --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \
48.   --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \
49.   --add-dir /src/Miadi
50. ```
51. 
52. ### Artefact-heavy deep-search session
53. 
54. ```bash
55. copilot \
56.   --plugin-dir /workspace/repos/jgwill/miadi-orchestration-kit/copilot/stckin-orchestration-kit \
57.   --add-dir /workspace/repos/jgwill/miadi-orchestration-kit \
58.   --add-dir /workspace/repos/miadisabelle/mia-awesome-copilot \
59.   --add-dir /src/Miadi \
60.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a \
61.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--karpathy--LLM-Wiki--and--RISE-Framework--QMD-Episodic--implication--2604210620--c08d048c-8710-439f-b1a2-542d3ed39df5 \
62.   --add-dir /src/IAIP/prototypes/artefacts/deep-search--CTXL--Context-Layers-in-Agentic-AI--Semantic-Layers--Ontologies--Provenance--and--Decision-Memory--2604230252--b1708f9f-328f-4fa0-b775-16c45b7c5d85
63. ```
64. 
65. ## Decisions
66. 
67. 1. Keep one strong first-wave kit instead of creating a second shallow research-only kit immediately.
68. 2. Encode deep-search behavior as a dedicated agent/skill pair inside the same kit for now.
69. 3. Leave `/src/Miadi` unchanged in this wave; the mission here was kit creation, not runtime hook modification.
70. 
71. ## Proposed next wave
72. 
73. 1. Exercise the kit in a fresh `copilot --plugin-dir` session and refine any prompt friction.
74. 2. Add a second kit only if a distinct research-only mode proves materially different from the STCKin orchestration flow.
75. 3. If a later wave touches `/src/Miadi`, wire the kit prompts to the actual STC launch and reporting paths with tests or simulators in that repo.
76.

_{⏱️ 3m 22s}

✅ bash

Validate plugin manifest and inspect created files

$ cd /workspace/repos/jgwill/miadi-orchestration-kit && jq . copilot/stckin-orchestration-kit/.github/plugin/plugin.json >/dev/null && printf 'plugin.json ok\n' && find copilot/stckin-orchestration-kit -maxdepth 4 -type f | sort && printf '\n--- git status ---\n' && git --no-pager status --short

plugin.json ok
copilot/stckin-orchestration-kit/agents/miadi-deep-search-synthesizer.md
copilot/stckin-orchestration-kit/agents/miadi-orchestration-architect.md
copilot/stckin-orchestration-kit/.github/plugin/plugin.json
copilot/stckin-orchestration-kit/README.md
copilot/stckin-orchestration-kit/skills/stckin-artefact-report/SKILL.md
copilot/stckin-orchestration-kit/skills/stckin-orchestration-scaffold/SKILL.md
copilot/stckin-orchestration-kit/skills/stckin-wave-bootstrap/SKILL.md

--- git status ---
 M README.md
?? copilot/stckin-orchestration-kit/
<exited with exit code 0>

_{⏱️ 3m 22s}

✅ sql

Finish orchestration todos

{
  "description": "Finish orchestration todos",
  "query": "UPDATE todos SET status = 'done' WHERE id IN ('build-kit', 'write-artefact-report');"
}

2 row(s) updated.

_{⏱️ 3m 35s}

💬 Copilot

Created a reusable first-wave Copilot kit at copilot/stckin-orchestration-kit and recorded the wave in .../deep-search--Miadi-STCKIN--copilot-orchestration-kit--2604251232--a4b4ed72-13a4-453d-9585-1c2fbcc5533a/first-wave-report.md.

The kit now includes:

1. Plugin packaging: .github/plugin/plugin.json with Miadi-specific agents and skills.
2. Agents: miadi-orchestration-architect.md and miadi-deep-search-synthesizer.md.
3. Skills: the refined stckin-wave-bootstrap, plus stckin-orchestration-scaffold and stckin-artefact-report.
4. Docs: updated repo README.md and kit README.md with concrete copilot --plugin-dir and --add-dir launch patterns.

I kept this wave to one strong kit instead of creating a second shallow research-only kit. That decision, the source-pattern findings from mia-awesome-copilot, and the proposed next wave are all captured in the artefact report.

_{Generated by GitHub Copilot CLI}