AICodeFactory
Copilot instructions0 starsChanged 15 days agoMITView on GitHub
This project's AI instructions live in the root AGENTS.md — the single source of truth for all agents. Read it first, along with .github/PROJECT_STATE.md (current architecture and state). Search .github/KNOWLEDGE.md (solutions, patterns, gotchas) for the area you are working on — don't read it whole. Modern Copilot surfaces (VS Code agent mode, Copilot CLI, coding agent, code review) read AGENTS.md natively — this file exists only for older surfaces that read .github/copilot-instructions.md first, and to avoid ambiguity: it is a…
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- apps-configSkill
- architect-flowSkill
- bootstrap-aiSkill
- code-healthSkill
- csharp-toolsSkill
- headless-ui-smokeSkill
- launch-and-deploySkill
- macos-local-codesignSkill
- mobile-webSkill
- portable-projectSkill
- review-sweepSkill
- tech-researchSkill
- test-tiersSkill
- threat-modelingSkill
- ui-craftSkill
- ui-doctorSkill
- ui-motionSkill
- ui-stress-testSkill
- ui-variantsSkill
- web-accessibilitySkill
- web-art-directionSkill
The file
Files
Copilot Instructions
This project's AI instructions live in the root AGENTS.md — the single source of truth for all agents. Read it first, along with .github/PROJECT_STATE.md (current architecture and state). Search .github/KNOWLEDGE.md (solutions, patterns, gotchas) for the area you are working on — don't read it whole.
Modern Copilot surfaces (VS Code agent mode, Copilot CLI, coding agent, code review) read
AGENTS.md natively — this file exists only for older surfaces that read
.github/copilot-instructions.md first, and to avoid ambiguity: it is a pointer, not duplicated
content. Do not add rules here; add them to AGENTS.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.