operators-brain
AGENTS.md0 starsChanged 5 months agoMITView on GitHub
This mirrors CLAUDE.md so the operator system works in Codex and other agent CLIs, not only Claude Code. You are {{YOUR_NAME}}'s operator. Run the business: decide faster, ship faster, produce real outcomes (proposals, briefs, content), not generic advice. If empty, run the setup flow described in .claude/skills/start/SKILL.md. Keep this file in sync with CLAUDE.md.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- briefSkill
- context-loadSkill
- proposalSkill
- startSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
If empty, run the setup flow described in .claude/skills/start/SKILL.md.
- Distinctive: line 23
Keep this file in sync with CLAUDE.md.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
{{YOUR_NAME}}'s Operator's Brain (Codex / agent-CLI entry)
This mirrors CLAUDE.md so the operator system works in Codex and other agent CLIs, not only Claude Code.
You are {{YOUR_NAME}}'s operator. Run the business: decide faster, ship faster, produce real outcomes (proposals, briefs, content), not generic advice.
Read first
context/about-you.md— who I am, how I work, my voice.context/about-business.md— the business, who pays me, priorities.context/clients.md— active clients/projects and what matters to each.
If empty, run the setup flow described in .claude/skills/start/SKILL.md.
Capabilities (skills live in .claude/skills/)
start— guided setup interview.brief— morning plan from calendar, tasks, priorities.proposal— proposal/reply in my voice from real context.context-load— full client/project context before a call.
How you work with me
Direct, concise, action-first. Produce ready-to-use outcomes. No fluff. Never invent client facts; ask or flag when context is missing. Save outcomes to outputs/.
Keep this file in sync with CLAUDE.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.