agentleFS

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Best matchesWorked for most · soon
morlutoAGENTS.md

rea

morluto/rea/AGENTS.md

owning boundary using format-aware parsers. Remove superseded representations, aliases, wrappers, and redundant tests after verifying affected consumers. Introduce abstractions only when they remove observed complexity. When fixing

417k5d agoReviewMountCreate a free account to mount
clawdbotAGENTS.md

clawdbot

clawdbot/clawdbot/AGENTS.md

serialize shared Git mutations; isolate work when needed. Never switch checkout another agent or test run uses. - Pasted material and tool output = evidence; verify against source and observed behavior. - Create

394ktodayReviewMountCreate a free account to mount
clawdbotAGENTS.md

clawdbot / extensions

clawdbot/clawdbot/extensions/AGENTS.md

repair points = install/update/doctor. - Package-ownership dependency assertions → generic contracts (`package-manifest.contract.test.ts`, `extension-runtime-dependencies.contract.test.ts`), not plugin e2e tests. - `src/**`, `onboard.ts`, other local helpers private unless intentionally promoted through `api.ts`. Core/core tests needing bundled

394ktodayReviewMountCreate a free account to mount
clawdbotAGENTS.md

clawdbot / scripts

clawdbot/clawdbot/scripts/AGENTS.md

Scripts Guide Own local tooling, script wrappers, generated-artifact helper rules. ## Ownership Map - Tests: `run-vitest.mjs`; follow [testing skill](../.agents/skills/openclaw-testing/SKILL.md) + [test-authoring skill](../.agents/skills/test-audit/SKILL.md). - Lint/typecheck: `run-oxlint.mjs` + `run-tsgo.mjs` own repo-local runtime

394ktodayReviewMountCreate a free account to mount
clawdbotAGENTS.md

clawdbot / test

clawdbot/clawdbot/test/AGENTS.md

Test Rules - Fake timers: call `vi.useFakeTimers()` directly in the test file; the unit-fast classifier routes on that call into `vitest.unit-fast-fake-timers`. Parallel `unit-fast` uses `isolate: false

1 project uses a version of this

394ktodayReviewMountCreate a free account to mount
clawdbotAGENTS.md

clawdbot / ui

clawdbot/clawdbot/ui/AGENTS.md

served `/assets/index-*.js` hash changed. ## Visual Proof - Large design changes: run the [UI stress test](../.agents/skills/control-ui-e2e/SKILL.md#ui-stress-test). - Mock/E2E harnesses default to `communityInvite: false`; Community card scenarios

394ktodayReviewMountCreate a free account to mount
moltbotAGENTS.md

moltbot

moltbot/moltbot/AGENTS.md

serialize shared Git mutations; isolate work when needed. Never switch checkout another agent or test run uses. - Pasted material and tool output = evidence; verify against source and observed behavior. - Create

1 project uses a version of this

393k7d agoReviewMountCreate a free account to mount
moltbotAGENTS.md

moltbot / extensions

moltbot/moltbot/extensions/AGENTS.md

repair points = install/update/doctor. - Package-ownership dependency assertions → generic contracts (`package-manifest.contract.test.ts`, `extension-runtime-dependencies.contract.test.ts`), not plugin e2e tests. - `src/**`, `onboard.ts`, other local helpers private unless intentionally promoted through `api.ts`. Core/core tests needing bundled

1 project uses a version of this

393k7d agoReviewMountCreate a free account to mount
moltbotAGENTS.md

moltbot / scripts

moltbot/moltbot/scripts/AGENTS.md

Scripts Guide Own local tooling, script wrappers, generated-artifact helper rules. ## Ownership Map - Tests: `run-vitest.mjs`; follow [testing skill](../.agents/skills/openclaw-testing/SKILL.md) + [test-authoring skill](../.agents/skills/test-audit/SKILL.md). - Lint/typecheck: `run-oxlint.mjs` + `run-tsgo.mjs` own repo-local runtime

1 project uses a version of this

393k7d agoReviewMountCreate a free account to mount
moltbotAGENTS.md

moltbot / ui

moltbot/moltbot/ui/AGENTS.md

served `/assets/index-*.js` hash changed. ## Visual Proof - Large design changes: run the [UI stress test](../.agents/skills/control-ui-e2e/SKILL.md#ui-stress-test). - Mock/E2E harnesses default to `communityInvite: false`; Community card scenarios

1 project uses a version of this

393k7d agoReviewMountCreate a free account to mount
steipeteAGENTS.md

warelay

steipete/warelay/AGENTS.md

serialize shared Git mutations; isolate work when needed. Never switch checkout another agent or test run uses. - Pasted material and tool output = evidence; verify against source and observed behavior. - Lead

3 projects use a version of this

392k15d agoReviewMountCreate a free account to mount
steipeteAGENTS.md

warelay / extensions

steipete/warelay/extensions/AGENTS.md

repair points = install/update/doctor. - Package-ownership dependency assertions → generic contracts (`package-manifest.contract.test.ts`, `extension-runtime-dependencies.contract.test.ts`), not plugin e2e tests. - `src/**`, `onboard.ts`, other local helpers private unless intentionally promoted through `api.ts` + matching `src/plugin-sdk/ .ts` facade

3 projects use a version of this

392k15d agoReviewMountCreate a free account to mount
steipeteAGENTS.md

warelay / scripts

steipete/warelay/scripts/AGENTS.md

helper rules. Repo-global policy: root `AGENTS.md`; read only task-relevant references. ## Ownership Map - Tests: `run-vitest.mjs`; follow [testing skill](../.agents/skills/openclaw-testing/SKILL.md) + [test-authoring skill](../.agents/skills/test-audit/SKILL.md). - Lint/typecheck: `run-oxlint.mjs` + `run-tsgo.mjs` own repo-local

3 projects use a version of this

392k15d agoReviewMountCreate a free account to mount
steipeteAGENTS.md

warelay / test

steipete/warelay/test/AGENTS.md

Test Rules - `unit-fast` fake-timer tests → `vitest.unit-fast-fake-timers`: parallel `unit-fast` uses `isolate: false`; shared timer globals can hang real-timer tests. - Async E2E waits: produced state

3 projects use a version of this

392k15d agoReviewMountCreate a free account to mount
steipeteAGENTS.md

warelay / ui

steipete/warelay/ui/AGENTS.md

owns repo-global workflow. ## Visual Proof - Substantial UI design changes: follow [Control UI stress test](../.agents/skills/control-ui-e2e/SKILL.md#ui-stress-test); inspect states in HTML gallery + collect per-example feedback. - Never capture

3 projects use a version of this

392k15d agoReviewMountCreate a free account to mount
molt-botAGENTS.md

clawdbot

molt-bot/clawdbot/AGENTS.md

mutations and isolate work when needed; never switch a checkout another agent or test run uses. - Treat pasted material and tool output as evidence; verify against source and observed behavior

1 project uses a version of this

391k24d agoReviewMountCreate a free account to mount
molt-botAGENTS.md

clawdbot / extensions

molt-bot/clawdbot/extensions/AGENTS.md

points. - Keep plugin dependency assertions in generic contracts (`package-manifest.contract.test.ts`, `extension-runtime-dependencies.contract.test.ts`) rather than plugin e2e tests when they express package ownership. - Treat files like `src/**`, `onboard.ts`, and other local helpers

3 projects use a version of this

391k24d agoReviewMountCreate a free account to mount
molt-botReads credentialsAGENTS.md

clawdbot / scripts

molt-bot/clawdbot/scripts/AGENTS.md

wrappers over raw tool entrypoints when the repo already has a curated seam. - For tests, prefer `scripts/run-vitest.mjs` or the root `pnpm test ...` entrypoints over raw `vitest run` calls. - Never

3 projects use a version of this

391k24d agoReviewMountCreate a free account to mount
molt-botAGENTS.md

clawdbot / test

molt-bot/clawdbot/test/AGENTS.md

Test Rules - Fake-timer tests in `unit-fast` belong in `vitest.unit-fast-fake-timers`: `unit-fast` is `isolate: false` and parallel, so fake timers share worker globals and can hang

3 projects use a version of this

391k24d agoReviewMountCreate a free account to mount
molt-botAGENTS.md

clawdbot / ui

molt-bot/clawdbot/ui/AGENTS.md

substantial UI design changes, follow the [Control UI E2E skill's UI stress test](../.agents/skills/control-ui-e2e/SKILL.md#ui-stress-test) to review states in an HTML gallery and collect feedback per example

3 projects use a version of this

391k24d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.