agentic-ways-of-working / adapters
AGENTS.md2 starsChanged 58 days agoMITView on GitHub
Adapter file for harnesses that read AGENTS.md (Codex CLI, and the growing set of tools adopting the convention). The canonical source is ../principles/working-style.md. Keep this a pointer. If your harness does not support includes, symlink this file to the canonical doc instead of copying it: ln -sf ../principles/working-style.md AGENTS.md The operative rules are in ../principles/working-style.md: Read that file in full before operating in a repo that links here.
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 31,439 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 repository14 other files it gives its agents.
- adapters/CLAUDE.mdCLAUDE.md
- blast-radiusSkill
- deepenSkill
- diagnoseSkill
- dispatch-waveSkill
- evidence-auditSkill
- grill-with-docsSkill
- session-closeoutSkill
- shipSkill
- symbol-surgerySkill
- tddSkill
- triageSkill
- write-a-skillSkill
- zoom-outSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Read that file in full before operating in a repo that links here.
≈ “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
Operator preferences
Adapter file for harnesses that read
AGENTS.md(Codex CLI, and the growing set of tools adopting the convention). The canonical source is../principles/working-style.md. Keep this a pointer. If your harness does not support includes, symlink this file to the canonical doc instead of copying it:ln -sf ../principles/working-style.md AGENTS.md
The operative rules are in ../principles/working-style.md:
- Decision bias — default to action, not confirmation.
- Canonical-pattern-first for infrastructure.
- Worktree isolation for parallel sessions.
- Prose-voice tasks load the voice guide first.
- Never fabricate the author's interior state.
- Secret handling — secrets manager, check existing first.
Read that file in full before operating in a repo that links here.
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.