saba
AGENTS.md1 starsChanged 19 days agoMITView on GitHub
The Python gateway owns agent execution, sessions, tools, memory, and security policy. WebUI and TUI share that runtime; keep execution and policy out of the clients.
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 repository4 other files it gives its agents.
- gemini-api-devSkill
- supabase-postgres-best-practicesSkill
- supabaseSkill
- typesafe-aiSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 21
Do not add defensive tests for hypothetical internal states or unsupported combinations.
- Distinctive: line 22
Do not add tests merely to prove that nonexistent behavior, removed code, or obsolete symbols are absent.
- Very specific: line 23
Do not run ruff format; mechanical formatting obscures git blame and creates unrelated diffs.
- Distinctive: line 24
Do not manually wrap prose in Markdown files.
≈ “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
Working on saba
The Python gateway owns agent execution, sessions, tools, memory, and security policy. WebUI and TUI share that runtime; keep execution and policy out of the clients.
Task-specific guidance
| When working on | Read |
| Core boundaries, extensions, or internal types | .agent/design.md |
| Refactoring, fallbacks, or test selection | .agent/simplify.md |
| User-facing copy, feature naming, or localization | .agent/copywriting.md |
| Path permissions, HTTP/MCP, or shell isolation | .agent/security.md |
| Dependency setup, WebUI transport, config, Windows, prompts, or persistence | .agent/gotchas.md |
| Reusing verification evidence | .agent/workflow.md |
| WebUI/host compatibility | .agent/review-guide.md |
| Contribution or publication | CONTRIBUTING.md, docs/releasing.md |
Development constraints
- Analyze the required behavior, state ownership, and root cause before extending existing code. Refactor when the structure causes the problem; a smaller diff does not justify another fallback.
- Do not add defensive tests for hypothetical internal states or unsupported combinations. Each new test needs a reachable path and a meaningful contract to protect.
- Do not add tests merely to prove that nonexistent behavior, removed code, or obsolete symbols are absent. Negative assertions must exercise a concrete, reachable risk and protect an observable behavioral contract; prefer testing supported actions and their results.
- Do not run
ruff format; mechanical formatting obscures git blame and creates unrelated diffs. This constraint takes precedence over the optional touched-file formatting inCONTRIBUTING.md. - Do not manually wrap prose in Markdown files. Keep each paragraph on one source line; use line breaks only for Markdown structure.
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.