system-agents-template
AGENTS.md2 starsChanged 4 months agoMITView on GitHub
This repository defines a file-based, turn-based multi-agent protocol.
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 31,774 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 repository10 other files it gives its agents.
- system-agents-turnSkill
- agent-system-check-updatesSkill
- agent-system-diffSkill
- agent-system-updateSkill
- check-chatroomSkill
- check-mentionsSkill
- end-turnSkill
- recruitSkill
- reportSkill
- send-messageSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Treat chatrooms/PROTOCOL.md and tasks/PROTOCOL.md as the source of truth.
- Very specific: line 10
When acting as an agent turn, prefer the $system-agents-turn skill if it is available.
- Very specific: line 11
Keep platform-neutral protocol behavior in chatrooms/, tasks/, and bot/.
- Very specific: line 15
After changing task parsing or turn-bot behavior, run python -m unittest bot/test_turn_bot.py -v.
- Very specific: line 16
After changing the Codex protocol guard, run python -m unittest bot/test_codex_chat_guard.py -v.
- Very specific: line 17
After changing the updater, run pytest bot/tests -q.
≈ “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
System Agents Template
This repository defines a file-based, turn-based multi-agent protocol.
Codex Guidance
- Treat
chatrooms/PROTOCOL.mdandtasks/PROTOCOL.mdas the source of truth. tasks/board.yamlis read-only for agents. Do not edit it directly. Send atask-create,task-update,task-claim, ortask-donemessage instead.- Chatroom messages are append-only. Do not edit an existing message file; write a new message file to correct or supersede it.
- When acting as an agent turn, prefer the
$system-agents-turnskill if it is available. - Keep platform-neutral protocol behavior in
chatrooms/,tasks/, andbot/. Keep model or client adapters in platform-specific folders such as.claude/,.codex/, and.agents/skills/.
Validation
- After changing task parsing or turn-bot behavior, run
python -m unittest bot/test_turn_bot.py -v. - After changing the Codex protocol guard, run
python -m unittest bot/test_codex_chat_guard.py -v. - After changing the updater, run
pytest bot/tests -q.
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.