agentleFS
AlwurtsAlwurts/simple-ai/AGENTS.md

simple-ai

AGENTS.md755 starsChanged 2 months agoMITView on GitHub

Tier-1 entry for anyone working in this repo, human or agent. Commands, conventions, and an index. Follow the links for detail. AGENTS.md and .claude/CLAUDE.md are kept byte-identical — mirrored as real copies, not a symlink. Change one, copy it over the other. Run from the monorepo root: After changing a registry item, run generate and commit registry.json, packages/registry/src/generated.ts, and apps/docs/public/r. - This is a shadcn registry of agent examples, not a finished app and not a chat-component kit. chat-page is…

  • 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 repository3 other files it gives its agents.

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Run from the monorepo root:

    line 11
  2. Very specific:

    After changing a registry item, run generate and commit registry.json, packages/registry/src/generated.ts, and apps/docs/public/r.

    line 23
  3. Distinctive:

    Prefer no code comments. Comment only when names and types cannot express an invariant, hazard, or external constraint.

    line 37

≈ “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

AGENTS.md

Tier-1 entry for anyone working in this repo, human or agent. Commands, conventions, and an index. Follow the links for detail.

AGENTS.md and .claude/CLAUDE.md are kept byte-identical — mirrored as real copies, not a symlink. Change one, copy it over the other.

Commands

Run from the monorepo root:

TaskCommand
Installpnpm install
Generate registrypnpm --filter @workspace/registry generate
Check generated filespnpm --filter @workspace/registry generate:check
Docs dev (port 4567)pnpm --filter docs dev
Typecheckpnpm typecheck
Lint (check)pnpm lint:check
Lint (fix)pnpm lint:fix

After changing a registry item, run generate and commit registry.json, packages/registry/src/generated.ts, and apps/docs/public/r.

Conventions

  • This is a shadcn registry of agent examples, not a finished app and not a chat-component kit. chat-page is the example you copy. shadcn is how you add it.
  • Gallery and chat-page stay mocked. Do not wire a live model into the docs site.
  • Documented UI is listed in apps/docs/content/docs/components/meta.json. shell and reasoning are registry internals that chat-page pulls in.
  • Item docs / envVars (when present) are the CLI post-add instructions. Keep them in sync with Installation.
  • Prefer no code comments. Comment only when names and types cannot express an invariant, hazard, or external constraint.
  • Public host is https://www.simple-ai.dev. Hosted items are /r/{name}.json.

Where things live

  • What the system is → docs/architecture.md
  • How to add or change a registry item → skill registry
  • Human setup → README.md, CONTRIBUTING.md
  • Release → RELEASING.md
  • Local shadcn add smoke → TESTING.md

Skills

Canonical copies live in .agents/skills/. .claude/skills/ is relative symlinks into that tree.

SkillWhy load it
architectureLayout of apps/packages and the catalog rules
registryItem defs, generate, dual registry, mocked gallery

Load the matching skill before changing registry source or the docs app structure.

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.