orchestrator
AGENTS.md1 starsChanged 2 months agoMITView on GitHub
This checkout is the public distribution of a Claude Code configuration stack. CLAUDE.md is an installation template; preserve its user-facing role. Change this checkout, never the developer's live ~/.claude or vault to test it.
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
- arch-reportSkill
- geo-lead-parserSkill
- oprosi-menyaSkill
- video-montageSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 1 is common, 4 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈4
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 7
Use Python 3.10+ and python -m unittest discover -s tests -v for portable core checks.
- Distinctive: line 13
Keep PowerShell wrappers ASCII.
- Common: line 14
Treat paths, shell commands and transcripts as untrusted inputs.
- Distinctive: line 15
Do not run optional media scripts on real inputs during tests.
- Distinctive: line 16
No auto-export or remote sync on installation.
- Distinctive: line 17
Do not claim Codex runtime compatibility from the presence of this file.
≈ “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
Orchestrator development
This checkout is the public distribution of a Claude Code configuration stack.
CLAUDE.md is an installation template; preserve its user-facing role.
Change this checkout, never the developer's live ~/.claude or vault to test it.
- Use Python 3.10+ and
python -m unittest discover -s tests -vfor portable core checks. CLAUDE_HOMEoverrides the stack being inspected. Tests must use disposable roots.- Guards are heuristic defense in depth, not a replacement for host permissions.
- A missing dependency or unexecuted check must not be reported as a pass.
- Sync must use an explicit manifest and must preserve an existing user index.
- Changes to guards, validators or sync require a regression that rejects the broken case.
- Keep PowerShell wrappers ASCII; existing localized scripts require UTF-8 BOM for Windows PowerShell 5.1.
- Treat paths, shell commands and transcripts as untrusted inputs. Do not include their secrets in diagnostics.
- Do not run optional media scripts on real inputs during tests; some are project-specific recipes.
- No auto-export or remote sync on installation. Both require explicit configuration.
- Do not claim Codex runtime compatibility from the presence of this file.
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.