personal-ai-os
CLAUDE.md4 starsChanged 7 months agoMITView on GitHub
Before working in this repo, read these files first: Treat those files as the active collaboration memory. Do not assume chat history is the source of truth. Current expectation: After finishing work: Append a short handoff entry to docs/agent-handoff.md.
In this repositoryOne other file it gives its agents.
- nepm-kernelSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Before working in this repo, read these files first:
- Distinctive: line 10
Treat those files as the active collaboration memory.
- Distinctive: line 11
Do not assume chat history is the source of truth.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Claude Code Collaboration Context
Before working in this repo, read these files first:
docs/agent-context.mddocs/ownership.mddocs/alignment-contract.mdif touching alignmentdocs/agent-handoff.md
Treat those files as the active collaboration memory. Do not assume chat history is the source of truth.
Current expectation:
- Claude Code owns backend, structure-layer work, contracts, and cross-file API wiring
- Codex owns frontend Quiet OS implementation, UI structure, and frontend integration once contracts are stable
After finishing work:
Append a short handoff entry to docs/agent-handoff.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.

