How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
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.
moltbotAGENTS.mdmoltbot/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
4 projects use a version of this
moltbotAGENTS.mdmoltbot/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
6 projects use a version of this
moltbotAGENTS.mdmoltbot/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
4 projects use a version of this
clawdbotAGENTS.mdclawdbot/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
1 project uses a version of this
clawdbotAGENTS.mdclawdbot/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
1 project uses a version of this
molt-botAGENTS.mdmolt-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
No other project uses it yet
molt-botAGENTS.mdmolt-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
2 projects use a version of this
molt-botAGENTS.mdmolt-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
molt-botAGENTS.mdmolt-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
obraAGENTS.mdobra/superpowers/AGENTS.md
skill philosophy differs from Anthropic's published guidance on writing skills. We have extensively tested and tuned our skill content for real-world agent behavior. PRs that restructure, reword
Steady7 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/apps/cli/tests/profiles/AGENTS.md
AGENTS.md — Profile integration tests This tree owns cross-package behavior of shipped `dsh` profiles. Start product scenarios through `apps/cli/src/bin.ts` with `--profile ` or the ` ` shorthand; a test-only Loader driver
Steady3 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/benchmarks/AGENTS.md
local diagnostics remain beside their owners and use the `.perf.ts` suffix instead of joining `test:bench`. - Organize benchmarks by measured user path, one directory per path. Do not mirror
Steady3 mentions in 2 weeks
1 project uses a version of this
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/docs/AGENTS.md
widen that scope. A reference may be exhaustive only about its own subject. Testing mechanisms, fixtures, and harnesses belong at the lowest owning level; higher documents link there. Classify every
Steady3 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/.github/AGENTS.md
steps on the default POSIX shell; shared entrypoints are Node scripts. Test and production jobs use separate `desktop-test` and `desktop-production` approval Environments after a credential-free preparation
Steady3 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/native/system/AGENTS.md
implementation. - Runtime binary selection has no environment-variable overrides. `NALR_REQUIRE_LANDLOCK` is a test-only enforcement requirement. - There is no install-time compile fallback. Missing Landlock binaries probe unusable
Steady3 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/packages/AGENTS.md
global service store ([postmortem](../docs/postmortem/0001-acp-default-export-drops-inject.md)). - **Product-visible plugins require a non-unit REAL-composition test.** Hand-built `ctx.plugin(...)` suites are insufficient. Boot test-only `cordis.yml` through the Loader and app/process
Steady3 mentions in 2 weeks
1 project uses a version of this
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/packages/experimental/AGENTS.md
shipped compositions in CI. Experimental packages may depend on release packages and each other. Tests may use experimental packages through `devDependencies`; examples may load them explicitly. - Experimental status does
Steady3 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/packages/schedule/AGENTS.md
delivery. - Keep recurrence arithmetic pure. Production uses platform wall time and segmented timers; tests use explicit samples or restored fake timers
Steady3 mentions in 2 weeks
No other project uses it yet
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/scripts/AGENTS.md
ownership gates use syntax-aware discovery, guard against an empty or narrowed corpus, and test every admitted/excluded form that changes their detection boundary. Script specs run in forked workers beside
Steady3 mentions in 2 weeks
5 projects use a version of this
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/snapshots/AGENTS.md
AGENTS.md — Recorded-session snapshots This tree contains only tests whose committed session JSONL is replay input and expected persisted output. Keep non-session ARIA, geometry, generator, CLI, and unit expected
Steady3 mentions in 2 weeks
1 project uses a version of this
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
