agentleFS
domucchidomucchi/pi-setup/AGENTS.md

pi-setup

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

Global guidance loaded into every pi session in this environment. Keep it short — it costs tokens on every request. Tool mechanics live in each extension's prompt.ts; this file is for cross-cutting behavior only. - Lead with the outcome; keep status notes brief. - Verify changes with a runnable check (tests, typecheck) before calling work done, and report the result honestly. - Ask one clarifying question only when the answer changes what you build. - Use subagents for self-contained work…

  • 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 repository5 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    Verify changes with a runnable check (tests, typecheck) before calling work done, and report the result honestly.

    line 10
  2. Distinctive:

    Ask one clarifying question only when the answer changes what you build.

    line 12
  3. Distinctive:

    Use subagents for self-contained work whose full output would clutter this context, or for parallel fan-out.

    line 16
  4. Distinctive:

    Run a workflow only when explicitly asked, or after proposing one and getting agreement.

    line 18
  5. Distinctive:

    Add a dependency with the package manager, not by hand-editing manifests.

    line 25
  6. Very specific:

    Run check/format/lint after a change when those commands exist.

    line 26

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Agent guidance

Global guidance loaded into every pi session in this environment. Keep it short — it costs tokens on every request. Tool mechanics live in each extension's prompt.ts; this file is for cross-cutting behavior only.

Working style

  • Lead with the outcome; keep status notes brief.
  • Verify changes with a runnable check (tests, typecheck) before calling work done, and report the result honestly.
  • Ask one clarifying question only when the answer changes what you build.

Delegation

  • Use subagents for self-contained work whose full output would clutter this context, or for parallel fan-out. Give each a complete prompt.
  • Run a workflow only when explicitly asked, or after proposing one and getting agreement.

TypeScript

  • Lean on inference; avoid explicit return types unless needed.
  • as any is a last resort — prefer real types.
  • Add a dependency with the package manager, not by hand-editing manifests.
  • Run check/format/lint after a change when those commands exist.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.