agentleFS
Sign inStart free
rust-uirust-ui/ui/AGENTS.md

ui

AGENTS.md727 starsChanged 21 days agoMITView on GitHub

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
  1. Very specific:

    Don't use Claude Code auto-memory for this project.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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
  • Cargo clippy: When finishing a task, run clippy scoped to the crate(s) you touched (cargo clippy -p <crate> --no-deps), in background, not --workspace --all-targets (recompiles every crate across all 3 target profiles: wasm/ios/server, very slow). Only widen to --workspace --all-targets if the change touched a public API (signature, struct field, trait) that other crates consume; CI already runs the full workspace check on the PR, so it's a safety net either way. sccache is wired globally as RUSTC_WRAPPER (user's ~/.cargo/config.toml, not committed to this repo since it's public) to share compile cache across the wasm/ios/server target profiles. Skip clippy entirely for trivial/CSS-only changes (Tailwind class string edits, comments, formatting) — no need to compile for those.
  • Git hooks: repo ships a pre-commit hook (typos check on staged files, needs typos-cli) in .githooks/, not auto-enabled by git. Each clone must run git config core.hooksPath .githooks once.
  • Changelog + versioning: keep CHANGELOG_DEV.md up to date (Keep a Changelog format, entries land under ## [Unreleased]). Semver tags are vMAJOR.MINOR.PATCH (annotated tags, current: v0.1.0), separate from the deploy_prod_v2_* timestamp tags. When [Unreleased] has grown enough to be worth cutting, tell me and propose the next version, then wait for me to confirm before renaming the section, tagging, and pushing.

Memory

  • Don't use Claude Code auto-memory for this project. Project knowledge/learnings live in __SKILLS_LEARNINGS/LEARNINGS.md (Confirmed + Inbox sections) — read it for context, write new entries there per the Self improving rule below.

Self improving

  • When I correct a behavior/pattern/preference (not a one-off fact) and you judge it will recur, append one bullet under ## Inbox in __SKILLS_LEARNINGS/LEARNINGS.md (YYYY-MM-DD [domain] avoid X, do Y, because Z) and mirror it to auto-memory as feedback. You decide, no keyword. Then print: 📝 learning saved: "<one-line>" (say "drop it" to undo). Skip: project trivia, anything already enforced by lint/tsconfig/biome/CI, low-confidence guesses. learn this forces it.

Download now (ZIP)

  • 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 28,693 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 repository2 other files it gives its agents.

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.

Check your setup, free