agentleFS

AGENTS.md examples from real projects

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

Worked for most · soon
SentryAGENTS.md

sentry / action_log

getsentry/sentry/src/sentry/issues/action_log/AGENTS.md

Action log entries are kept effectively forever and are never migrated. Read the GroupAction docstring in types.py before adding or changing a GroupAction subclass.

No other project uses it yet

46k5mo agoReviewMountCreate a free account to mount
SentryAGENTS.md

sentry / derived

getsentry/sentry/src/sentry/issues/derived/AGENTS.md

Follow README.md in this directory when changing Features or aggregators here.

No other project uses it yet

46k5mo agoReviewMountCreate a free account to mount
SentryAGENTS.md

sentry / static

getsentry/sentry/static/AGENTS.md

For critical commands and testing rules, see the "Command Execution Guide" section in /AGENTS.md in the repository root. - Routes defined in static/app/router/routes.tsx - Builds, tests, and typechecks use React…

No other project uses it yet

46k5mo agoReviewMountCreate a free account to mount
SentryAGENTS.md

sentry / api

getsentry/sentry/static/packages/api/AGENTS.md

Build from the repository root with the commands in the README's Development section. Run pnpm --filter @sentry/api run build before typecheck and test:vitest: both read the generated src/ and dist/…

46k5mo agoReviewMountCreate a free account to mount
SentryAGENTS.md

sentry / tests

getsentry/sentry/tests/AGENTS.md

For test commands (make test-selective, pytest), see the "Command Execution Guide" section in /AGENTS.md in the repository root. This guide covers Python tests. For frontend React/TypeScript tests (*.spec.tsx, RTL, MockApiClient),…

No other project uses it yet

46k5mo agoReviewMountCreate a free account to mount
LangChainAGENTS.md

langgraph

langchain-ai/langgraph/AGENTS.md

This repository is a monorepo. Each library lives in a subdirectory under libs/. When Corridor's analyzePlan tool is available, create a plan and use the tool to analyze it before generating or modifying code. Apply the resulting security guidance before writing code. When you modify code in any library, run the following commands in that library's directory before creating a pull request: To run a particular test file or to pass additional pytest options you can specify the TEST variable:

No other project uses it yet

45k21d agoReviewMountCreate a free account to mount
GitHubAGENTS.md

awesome-copilot

github/awesome-copilot/AGENTS.md

The Awesome GitHub Copilot repository is a community-driven collection of custom agents and instructions designed to enhance GitHub Copilot experiences across various domains, languages, and use cases. The project includes: All agent files (*.agent.md) and instruction files (*.instructions.md) must include proper markdown front matter. Agent Skills are folders containing a SKILL.md file with frontmatter and optional bundled assets. Hooks are folders containing a README.md with frontmatter and a hooks.json configuration file: Frontmatter must be valid YAML and meet the metadata…

41k22d agoReviewMountCreate a free account to mount
GitHubAGENTS.md

awesome-copilot / improve-history

github/awesome-copilot/skills/foundry-agentic-loop/evals/fixtures/improve-history/AGENTS.md

This workspace is built with spec-driven development. For build requests and the short commands below, load the foundry-agentic-loop skill and follow its references/sdd.md; it checks the live run first and resumes a running or paused run instead of starting a second one. - The spec and contract live in docs/spec.md, lessons in docs/LOOP.md and Azure settings only in .azure/deployment-plan.md, never here. - This section locks the build mode. Change it only when the user explicitly confirms a switch. <!-- foundry-agentic-loop:end…

No other project uses it yet

41k22d agoReviewMountCreate a free account to mount
GitHubAGENTS.md

awesome-copilot / rapid-locked

github/awesome-copilot/skills/foundry-agentic-loop/evals/fixtures/rapid-locked/AGENTS.md

Team conventions: Python formatted with ruff, TypeScript with prettier. This workspace is a rapid prototype in an existing Foundry project. For build requests, load the foundry-agentic-loop skill and follow its references/rapid.md. Short commands: - The contract lives in the root README.md, lessons in docs/LOOP.md and Azure settings only in .azure/deployment-plan.md, never here. - This section locks the build mode. Change it only when the user explicitly confirms a switch. <!-- foundry-agentic-loop:end -->

No other project uses it yet

41k22d agoReviewMountCreate a free account to mount
GitHubAGENTS.md

awesome-copilot / team-conventions

github/awesome-copilot/skills/foundry-agentic-loop/evals/fixtures/team-conventions/AGENTS.md

No summary in the file. Open it to read it.

No other project uses it yet

41k22d agoReviewMountCreate a free account to mount
GitHubAGENTS.md

awesome-copilot / templates

github/awesome-copilot/skills/repo-standardizer/templates/AGENTS.md

Telegraph style. Root rules only. Guidance for AI coding agents (Claude Code, Cursor, Copilot, OpenClaw, etc.) working in this repository.

1 project uses a version of this

41k22d agoReviewMountCreate a free account to mount
GitHubAGENTS.md

awesome-copilot / templates

github/awesome-copilot/skills/setup-my-iq/assets/templates/AGENTS.md

These pointers tell agents where the user's personal context files live. Read only the file(s) needed to answer a question; do not load all of them by default. Run the setup-my-iq skill to populate these context files (or fill them in manually). Once they exist, update each @<path> pointer below to reference the real location. - identityProfile — name, role, org, team, manager, what the user does, what people come to them for. @<CONTEXT_DIR>/identity.md - roleAndResponsibilities — responsibilities per team,…

No other project uses it yet

41k22d agoReviewMountCreate a free account to mount
PostHogAGENTS.md

posthog

PostHog/posthog/AGENTS.md

- Environment: - Check which environment is available before installing dependencies or starting services. A local checkout is not necessarily a full Linux dev environment. When the host lacks Docker…

41k3d agoReviewMountCreate a free account to mount
PostHogAGENTS.md

posthog / common

PostHog/posthog/common/AGENTS.md

common/ is a transitional holding pen, not a destination. It holds shared code that predates a better home. Do not treat it as the default place for new shared code.

1 project uses a version of this

41k3d agoReviewMountCreate a free account to mount
PostHogAGENTS.md

posthog / ee

PostHog/posthog/ee/AGENTS.md

Do not add a file to ee/. The folder is deprecated and new code belongs in posthog/ or products/<product>/. The .github/scripts/check-no-new-ee-files.py check fails a pull request that adds any new…

41k3d agoReviewMountCreate a free account to mount
PostHogAGENTS.md

posthog / hog

PostHog/posthog/hog/AGENTS.md

hog is the PostHog command line, version 1. Read README.md for what it does and how to run it. Import from another folder with @/, which tsconfig.json maps to src/,…

41k3d agoReviewMountCreate a free account to mount
PostHogAGENTS.md

posthog / proto

PostHog/posthog/proto/AGENTS.md

When you add or modify an RPC or message type in personhog/ protos, you must update all downstream consumers before considering the change complete: Then update: Then update: No codegen…

1 project uses a version of this

41k3d agoReviewMountCreate a free account to mount
PostHogAGENTS.md

posthog / rust

PostHog/posthog/rust/AGENTS.md

When emitting metrics via the metrics crate (histogram!, counter!, gauge!), dynamic label values (method names, client names, etc.) must use Arc<str>, never String or .to_string(). A pull request builds no…

41k3d agoReviewMountCreate a free account to mount
MicrosoftAGENTS.md

playwright-mcp

microsoft/playwright-mcp/AGENTS.md

This repo ships the npm package @playwright/mcp. The MCP server itself is in microsoft/playwright, in packages/playwright-core/src/tools/: mcp/ has the server, its config and its command line options, and backend/ has the tools. - What this repo owns: cli.js and index.js, which run the server of the pinned playwright-core, the types, the README, the Dockerfile, and the tests of the packaged server. - What is a copy or an output: roll.js copies config.d.ts from packages/playwright-core/src/tools/mcp/config.d.ts, and npm run lint generates the…

Steady4 mentions in 2 weeks

No other project uses it yet

40k6d agoReviewMountCreate a free account to mount
VercelReads credentialsAGENTS.md

skills

vercel-labs/skills/AGENTS.md

This file provides guidance to AI coding agents working on the skills CLI codebase. skills is the CLI for the open agent skills ecosystem. Aliases: skills a works for add. skills i, skills install (no args) restore from skills-lock.json. skills ls works for list. skills experimental_install restores from skills-lock.json. skills experimental_sync reads skills from npm dependencies (sync remains a compatibility alias).

Steady5 mentions in 2 weeks

No other project uses it yet

39k21d 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.