agentleFS

AGENTS.md examples from real projects

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

Best matches · from page 9Worked for most · soon
ansibleAGENTS.md

ansible

ansible/ansible/AGENTS.md

project. ## General Principles When reviewing code, don't flag issues that `ansible-test sanity` already catches. Focus review effort on things automated checks can't verify. ## Attribution Agents should disclose

No other project uses it yet

71k2mo agoReviewMountCreate a free account to mount
code-yeongyuAGENTS.md

oh-my-opencode

code-yeongyu/oh-my-opencode/.agents/AGENTS.md

isolated `CODEX_HOME` + local mock model, hook-fired assertions; helper scripts each ship `--self-test` | | `opencode-qa/` | no | opencode CLI/TUI/event-stream QA: hook-fired assertions via SSE, session DB inspection, tmux

1 project uses a version of this

71k10d agoReviewMountCreate a free account to mount
code-yeongyuAGENTS.md

oh-my-opencode / assets

code-yeongyu/oh-my-opencode/assets/AGENTS.md

bash bun run build:schema bun run build:omo-schema bun run script/build-help-schemas.ts bun test tests/omo-schema-freshness.test.ts ``` ## CONVENTIONS - Regenerate after changing the corresponding source schema or help definition. - Commit generated output

1 project uses a version of this

71k10d agoReviewMountCreate a free account to mount
code-yeongyuAGENTS.md

oh-my-opencode / bin

code-yeongyu/oh-my-opencode/bin/AGENTS.md

selector | | Version mismatch output | `version-mismatch.js` | User-facing installed-wrapper/platform-package mismatch diagnostics | | Behavior tests | `*.test.ts` | Bun tests for invocation routing, platform selection, and diagnostics | ## RUNTIME FLOW `oh-my-opencode.js` derives the invocation

1 project uses a version of this

71k10d agoReviewMountCreate a free account to mount
code-yeongyuAGENTS.md

oh-my-opencode / packages

code-yeongyu/oh-my-opencode/packages/AGENTS.md

PACKAGES | Package | Layout | Purpose | |---------|--------|---------| | `lsp-tools-mcp/` | Vendored standalone project (`.github/`, `CHANGELOG.md`, `LICENSE`, `src/`, `test/`, `biome.json`, `vitest.config.ts`) | Serves the 8 aliases `lsp_status`, `lsp_diagnostics`, `lsp_goto_definition`, `lsp_find

1 project uses a version of this

71k10d agoReviewMountCreate a free account to mount
code-yeongyuAGENTS.md

oh-my-opencode / scripts

code-yeongyu/oh-my-opencode/scripts/AGENTS.md

pack --dry-run --json` manifests | | `third-party-notice-requirements.mjs` | Declarative notice requirements and path/package matching | | `check-third-party-notices.test.mjs` | Node test coverage for spawn invocation resolution (Windows/non-Windows) and `parseNpmPackJson` (npm 11 array, npm 12 keyed, malformed

1 project uses a version of this

71k10d agoReviewMountCreate a free account to mount
docling-projectAGENTS.md

docling

docling-project/docling/AGENTS.md

inside the package (see below) packages/docling/ # full docling meta-package packages/docling-slim/ # slim package readme tests/ # pytest suite and test data docs/ # MkDocs documentation and examples scripts/ # project maintenance scripts ``` ## Skills

No other project uses it yet

70k39d agoReviewMountCreate a free account to mount
openinterpreterAGENTS.md

open-interpreter

openinterpreter/open-interpreter/AGENTS.md

with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations

Steady4 mentions in 2 weeks

1 project uses a version of this

69k4mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / integrations

mem0ai/mem0/integrations/AGENTS.md

agent-plugin-core/`. Check the table before running anything. | Directory | Package | Build | Lint | Test | |-----------|---------|-------|------|------| | `vercel-ai-sdk/` | `@mem0/vercel-ai-provider` | tsup (CJS+ESM) | ESLint + Prettier | jest + vitest (edge/node) | | `openclaw/` | `@mem0/openclaw-mem0` | tsup

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / mem0

mem0ai/mem0/mem0/AGENTS.md

commit make lint # ruff check make format # ruff format make sort # isort mem0/ make test # pytest tests/ make test-py-3.9 # pin a Python version (3.9 through 3.12) make install

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / skills

mem0ai/mem0/skills/AGENTS.md

repo through a TDD pipeline. Writes a feature branch plus `.mem0-integration/` artifacts. | | `mem0-test-integration/` | Verifies what the integrator produced, on the same branch. Read-only against the repo

Steady2 mentions in 2 weeks

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
mem0aiAGENTS.md

mem0 / tests

mem0ai/mem0/tests/AGENTS.md

Python SDK tests (`tests/`) pytest suite for the `mem0/` package. ## Commands ```bash make install_all # optional deps; several tests need them make test # pytest tests/ make test

Steady2 mentions in 2 weeks

No other project uses it yet

69k2mo agoReviewMountCreate a free account to mount
prometheusAGENTS.md

prometheus

prometheus/prometheus/AGENTS.md

skip histogram buckets when trimming feat(agent): fix ST append; add compliance RW sender test chore: fix emptyStringTest issues from gocritic ci: add statuses write permission to prombench workflow docs

No other project uses it yet

68k12d agoReviewMountCreate a free account to mount
apacheAGENTS.md

echarts

apache/echarts/AGENTS.md

TypeScript-first charting library. Most runtime code lives in `src/`, while build scripts, test utilities, and packaging logic live alongside it in dedicated top-level folders. One thing worth knowing

No other project uses it yet

67k4y agoReviewMountCreate a free account to mount
facebookAGENTS.md

docusaurus

facebook/docusaurus/AGENTS.md

components, and theme overrides - `_dogfooding/` - Hidden docs, blog and pages plugin instances for dogfooding, testing features and edge cases, making it easier to review on PR deploy previews ### Writing documentation

No other project uses it yet

67k8d agoReviewMountCreate a free account to mount
warpdotdevAGENTS.md

Warp

warpdotdev/Warp/AGENTS.md

endpoint (default: `http://localhost:8080`) - `WS_SERVER_URL` - WebSocket endpoint (default: `ws://localhost:8080/graphql/v2`) ### Testing - `cargo nextest run --no-fail-fast --workspace` - Run tests with nextest - `cargo test

Steady9 mentions in 2 weeks

2 projects use a version of this

66k11d agoReviewMountCreate a free account to mount
2dustAGENTS.md

v2rayNG

2dust/v2rayNG/AGENTS.md

exception; agent inference cannot. - `Task scope` is the named files and behavior plus dependency, test, or build edits that a compiler or required validation proves necessary. Every other change

Steady10 mentions in 2 weeks

No other project uses it yet

66k4y agoReviewMountCreate a free account to mount
traefikAGENTS.md

traefik

traefik/traefik/AGENTS.md

generate-webui` (Docker required) — they are not meant to be hand-edited. - `integration/` — integration tests; reusable fixtures under `integration/fixtures/`. - `docs/content/` — MkDocs sources for the public documentation. ## Before you edit Read

No other project uses it yet

65k4mo agoReviewMountCreate a free account to mount
scrapyAGENTS.md

scrapy

scrapy/scrapy/AGENTS.md

mypy` and `tox -e pylint`, and `tox -e docs` and `tox -e docs-tests` as well if you touched docs or docstrings. CI runs these first and skips the test

No other project uses it yet

65k59d agoReviewMountCreate a free account to mount
localstackAGENTS.md

localstack

localstack/localstack/AGENTS.md

cloud stack that emulates AWS services (S3, Lambda, DynamoDB, etc.) for development and testing. It runs in Docker, provides AWS-like APIs locally, enabling offline workflows, integration testing

65k15mo 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.