compabob
CLAUDE.md34 starsChanged 20 days agoMITView on GitHub
Claude Code loads this file every session. It imports the constitution and points at memory. @CONSTITUTION.md memory/MEMORY.md is injected at session start by hooks/hook-session-start.sh; read the file yourself only if it is missing from your context. It records the user's name, role, and working language, your own name, and the index of what you have learned about the user and their work. Follow its links into memory/topics/ only as needed. The knowledge base is vault/. Persistent facts are in memory/.…
In this repository21 other files it gives its agents.
- add-agentSkill
- build-listSkill
- chart-tufteSkill
- councilSkill
- design-precheckSkill
- document-exportSkill
- handoverSkill
- index-memorySkill
- log-decisionSkill
- mcp-debugSkill
- meeting-prepSkill
- memory-debtSkill
- merge-contactsSkill
- morning-briefSkill
- post-callSkill
- reflectSkill
- setupSkill
- system-auditSkill
- tasksSkill
- visual-explainerSkill
- weekly-reviewSkill
The file
Files
Compabob
Claude Code loads this file every session. It imports the constitution and points at memory.
@CONSTITUTION.md
Memory
memory/MEMORY.md is injected at session start by hooks/hook-session-start.sh; read the file yourself only if it is missing from your context. It records the user's name, role, and working language, your own name, and the index of what you have learned about the user and their work. Follow its links into memory/topics/ only as needed.
Working directory
The knowledge base is vault/. Persistent facts are in memory/. Your own configuration is in .claude/ and config/. vault/, memory/, and config/user.config.yaml are the user's own data and live outside the kit's version control. Everything else is the kit, and updates upstream.
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.