ai-agent-pipeline
Copilot instructions0 starsChanged 4 months agoMITView on GitHub
Project-specific rules live in .github/instructions/project/*.instructions.md Rules are canonical in .github/instructions/ — see README.md there for folder structure. Shared across Claude Code, Cursor, and GitHub Copilot. Documentation
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agents-entry.mdcCursor rule
- .cursor/rules/git-operations.mdcCursor rule
- maintain-agentsSkill
The file
Files
Copilot Instructions
Rules — Project-Specific
Project-specific rules live in .github/instructions/project/*.instructions.md
Rules — Global
Rules are canonical in .github/instructions/ — see README.md there for folder structure.
Shared across Claude Code, Cursor, and GitHub Copilot.
General
- General baseline:
.github/instructions/general.instructions.md
Code
- TypeScript patterns:
.github/instructions/code/typescript-patterns.instructions.md - Modern TS patterns:
.github/instructions/code/modern-typescript-patterns.instructions.md - Oxlint & style:
.github/instructions/code/linting-code-style.instructions.md - Provider/context patterns:
.github/instructions/code/provider-context-patterns.instructions.md - Picocolors CLI styling:
.github/instructions/code/picocolors-cli-styling.instructions.md
Naming
- File naming:
.github/instructions/naming/file-naming.instructions.md - Variable naming:
.github/instructions/naming/variable-naming.instructions.md
Documentation
- Documentation:
.github/instructions/documentation/documentation.instructions.md - README standards:
.github/instructions/documentation/readme-standards.instructions.md - Agent-facing markdown:
.github/instructions/documentation/agent-facing-markdown.instructions.md - Feature design specs:
.github/instructions/documentation/feature-design-specs.instructions.md - TODO/DONE docs:
.github/instructions/documentation/todo-done-docs.instructions.md
Git
- Git policy:
.github/instructions/git/git-policy.instructions.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.