company-brain-os
AGENTS.md7 starsChanged 47 days agoMITView on GitHub
This workspace is built Claude Code-first: skills, an auto-loaded CLAUDE.md, guided flows. If you are using a different agent (Cursor, Codex, Copilot, or another tool), or working by hand, start with CLAUDE.md. It is the constitution every convention in this repo follows, regardless of which agent is reading it. Outside Claude Code, you keep the brain: the markdown conventions, memory/, daily-log/, and the git flow, none of which depend on any particular tool. You lose the operating system: skills, auto-load,…
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- daily-log/CLAUDE.mdCLAUDE.md
- memory/CLAUDE.mdCLAUDE.md
- operators/CLAUDE.mdCLAUDE.md
- daily-briefingSkill
- handoverSkill
- html-previewSkill
- meeting-debriefSkill
- memory-checkupSkill
- pr-reviewSkill
- session-debriefSkill
- setup-company-brainSkill
- shipSkill
- skill-detectorSkill
- skill-improveSkill
- sparringSkill
- syncSkill
- system-checkupSkill
The file
Files
AGENTS.md
This workspace is built Claude Code-first: skills, an auto-loaded CLAUDE.md, guided
flows. If you are using a different agent (Cursor, Codex, Copilot, or another tool), or
working by hand, start with CLAUDE.md. It is the constitution every convention in this
repo follows, regardless of which agent is reading it.
Honest framing
Outside Claude Code, you keep the brain: the markdown conventions, memory/,
daily-log/, and the git flow, none of which depend on any particular tool. You lose
the operating system: skills, auto-load, and guided flows are what Claude Code adds on
top of the brain. Every skill-driven flow below has a manual equivalent: more typing,
same underlying structure.
| Skill-driven flow | Manual equivalent |
/sync | git pull, then read your teammates' recent daily logs for what changed. |
/session-debrief | Write today's entry in daily-log/YYYY-MM-DD-<your-slug>.md, update the relevant files in memory/ (including MEMORY.md's index line), then commit and push. |
/daily-briefing | Read MEMORY.md, then the last few days of daily logs, to build your own priority list before starting work. |
Everything else, resolving the active operator, naming a new area, filing something in
memory/, follows the same rules whether a skill runs it or you do it by hand: read the
relevant CLAUDE.md (root, memory/, operators/, daily-log/, or the area you are
touching) before acting.
None of this requires Claude Code. It requires reading the CLAUDE.md files and
following the same conventions yourself.
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.