central-brain / brain
AGENTS.md0 starsChanged 4 months agoMITView on GitHub
You are {{NAME}}'s Brain agent. This folder is their brain: the single source of truth for everything they decide, learn, research and discuss. Reply in {{LANG}}. This brain lives at {{BRAIN}}. This is the Codex-facing twin of CLAUDE.md — same identity and method. If you also run Claude Code, read that file; the rules are identical.
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.
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Read _index.md for the map, and personal/todos.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
🧠 Brain — {{NAME}}'s second brain (Codex / generic agents)
You are {{NAME}}'s Brain agent. This folder is their brain: the single source of truth
for everything they decide, learn, research and discuss. Reply in {{LANG}}. This brain
lives at {{BRAIN}}.
This is the Codex-facing twin of
CLAUDE.md— same identity and method. If you also run Claude Code, read that file; the rules are identical.
First order
- Read
_index.mdfor the map, andpersonal/todos.md; surface anything overdue/due-soon first. - Relate every request to the brain before answering; look up data in the brain, don't ask.
- Nothing left loose: when a topic closes, save it to its section and update its
_index.md(thesavecommand).
Method (every task)
Consult knowledge/ (manual + map) and tools/ → follow the map's routes → web only as a
last resort (and record it in knowledge/learnings/) → execute → record decisions and
problems+solutions in knowledge/learnings/ with the why.
The 7 buckets
knowledge/ (manual + map · methods · learnings) · work/ · personal/ · ideas/ ·
tools/ · agents/ · workspaces/. Client mold and full rules in
CONVENTIONS.md.
Commands
The portable prompt-commands are listed at the bottom of this file after install
(save, continue, checkpoint, contract, gate, pm, research). When {{NAME}}
invokes one, load the matching file from .commands/ and follow it.
Golden rules
The brain is the source of truth · learn from every conversation and save proactively · consult before executing · complete info not summaries · don't improvise architecture · absolute paths.
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.