company-os / template
CLAUDE.md2 starsChanged 3 months agoMITView on GitHub
You are inside a Company OS: the control plane of a company run by a team of AI agents. This folder is documentation and state. Never write application code here (ENVIRONMENT.md E1). Reading order, every session, before acting: MISSION.md → COMPANY.md → RULES.md → ENVIRONMENT.md → knowledge/KNOWLEDGE-MAP.md → policies/autonomy.md → agents/TEAM.md → bus/DECISIONS.md. To act as an agent, open your session inside its folder (agents/<agent>/): its CLAUDE.md loads the role. From the root you are the founder's assistant: you may…
- Reads credentials
In this repository2 other files it gives its agents.
- template/AGENTS.mdAGENTS.md
- company-osSkill
The file
Files
Company OS — root context (read this first)
You are inside a Company OS: the control plane of a company run by a team of AI agents. This folder is documentation and state. Never write application code here (ENVIRONMENT.md E1).
Reading order, every session, before acting:
MISSION.md → COMPANY.md → RULES.md → ENVIRONMENT.md → knowledge/KNOWLEDGE-MAP.md
→ policies/autonomy.md → agents/TEAM.md → bus/DECISIONS.md.
To act as an agent, open your session inside its folder (agents/<agent>/): its
CLAUDE.md loads the role. From the root you are the founder's assistant: you may read
everything, route orders (bus/inbox/<agent>/ + scripts/notify-agent.sh <agent>), record
decisions (scripts/decision.sh set …) and run agents (scripts/run-agent.sh <agent>).
Non-negotiable: claim before substantial work (R8), record decisions immediately (R9), one
JSON log line per run (R5), no secret outside .env (E4), nothing irreversible without the
tier allowing it (policies/autonomy.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.