rosetta
AGENTS.md373 starsChanged 5 days agoApache-2.0View on GitHub
Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when needed. Monorepo with multiple solution components in src and golden instructions in instructions. R3 is current, R2 is KTLO. Defines reusable plugins/mcp for AI coding agents (claude code, codex, copilot, cursor, antigravity, etc) which users (engineers, developers) invoke on THEIR target repositories. instructions folder…
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- collect-github-statsSkill
- compress-promptSkill
- daily-ossSkill
- documentationSkill
- merge-mainSkill
- sync-web-siteSkill
- update-change-logSkill
The file
Files
Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise.
Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when needed.
Monorepo with multiple solution components in src and golden instructions in instructions. R3 is current, R2 is KTLO.
Defines reusable plugins/mcp for AI coding agents (claude code, codex, copilot, cursor, antigravity, etc) which users (engineers, developers) invoke on THEIR target repositories.
instructions folder contains AI coding agent instructions for another repository (skills, subagents, rules, workflows), it is not documentation.
How it works:
- User installs Rosetta plugin(s) xor mcp.
- On any user session start: AI Coding Agents load
instructions/r3/core/rules/bootstrap-alwayson.mdand one mode-specific file (plugin-files-mode.md,mcp-files-mode.md,local-files-mode.md). - User uses
/or$commands to do his work on his repo with any or all our instructions (skills, subagents, workflows, rules).
Bump versions for changes in src folder if not bumped already, prefer patch increase (scripts/bump_versions.sh).
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.