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
OpenAIAGENTS.md

plugins / mobile-app

openai/plugins/plugins/product-design/templates/mobile-app/AGENTS.md

In ChatGPT Work Mode, run sites-preview start "$PWD", open http://terminal.local:4173/ in the cloud browser, and verify the rendered app and its primary interactions. Keep that preview open and tell the…

7.8k6mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

plugins / prototype

openai/plugins/plugins/product-design/templates/prototype/AGENTS.md

Run the local server yourself and open the preview in the browser available to this environment. Do not give the user server-start instructions when you can run it. Before making…

7.8k6mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

plugins / react-best-practices

openai/plugins/plugins/vercel/skills/react-best-practices/AGENTS.md

Version 1.0.0 Vercel Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React and Next.js codebases. Humans may also find…

7.8k6mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

plugins / zoom

openai/plugins/plugins/zoom/AGENTS.md

This repository contains the Zoom plugin for Codex. Its purpose is to help users and engineers:

7.8k6mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

harmony

openai/harmony/AGENTS.md

This project provides a structured way to create messages that get rendered into a set of tokens using our harmony prompt format. The majority of the code is written in Rust inside src/ and src/py_module.rs defines using pyo3 what functions are exposed to the python version of the library with a wrapper in python/openai_harmony/__init__.py. You can build the Rust code along with the Python wrapper using maturin develop --release. This will also locally install the library in the venv so…

4.5k16mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

openai-agents-js

openai/openai-agents-js/AGENTS.md

Read and follow CONTRIBUTING.md#security for credentials, diagnostics, dependencies, sensitive-change review, CI isolation, and release integrity; use SECURITY.md for scope and private vulnerability reporting. Public PR/review instructions do not authorize disclosure of undisclosed vulnerabilities or sensitive evidence. Read the applicable .agents/skills/<name>/SKILL.md and only its needed references. These triggers authorize skill use unless manual invocation is explicitly required. User instructions and approved scope override skill defaults, subject to permissions; do not repeat granted approvals. Apply the highest tier across the complete task-owned…

4k10mo agoReviewMountCreate a free account to mount
OpenAIReads credentialsAGENTS.md

openai-go

openai/openai-go/AGENTS.md

Most SDK source is Castiron-generated. Before editing, follow Modifying/Adding code to identify ownership; generated files may lack identifying headers. Fix recurring generated defects upstream and regenerate. Keep handwritten policy, automation, tests, and examples small; alter exported APIs only when explicitly required. Read and apply CONTRIBUTING.md#security-requirements for credentials, diagnostic redaction, dependency review, action pins, CI permissions, CODEOWNER review, and artifact-appropriate validation. Report vulnerabilities privately through SECURITY.md, never public issues/PRs/discussions. go.mod owns the technical minimum; read GO_VERSION_POLICY.md for support/grace/release rules. CI tests…

Steady21 mentions in 2 weeks

No other project uses it yet

3.5k3mo agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

openai-openapi

openai/openai-openapi/AGENTS.md

Read and follow CONTRIBUTING.md and SECURITY.md, including contribution eligibility, review, validation, and sensitive-data requirements. PRs are limited to OpenAI team members; external contributors use feedback.

2.6k9d agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

openai-java

openai/openai-java/AGENTS.md

Read CONTRIBUTING.md and SECURITY.md before changes. .castiron.stats.yml records generation metadata. Follow Generated-file ownership before editing SDK files. Apply Security expectations for credentials, diagnostics, dependency/build integrity, action pins, publishing permissions, security review, and private disclosure. Additional requirements: Large application/json bodies and streaming events are normal Responses, Chat Completions, and other API output. Do not add arbitrary fixed body/event/line limits as security or efficiency fixes. Any new rejection limit requires an explicit owner-approved API contract and review of supported payloads/transports. Preserve longstanding…

1.6k9d agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

openai-cli

openai/openai-cli/AGENTS.md

Before changing code, read and follow CONTRIBUTING.md and SECURITY.md. In particular: - Project structure, generated and handwritten code, and repository layout: package ownership, dependency direction, command compatibility, assembly order, safe help recovery, and the separate api_reference/go.mod module. Reuse existing packages; explain any new package's distinct responsibility. - Security requirements: credential handling, synthetic tests, diagnostic redaction, dependency/install review, the existing hourly SDK updater, workflow permissions, signing/publication boundaries, and required SDK CODEOWNER review. Review response-header logging independently; sanitize --debug output before sharing.…

Steady2 mentions in 2 weeks

No other project uses it yet

1.2k9d agoReviewMountCreate a free account to mount
OpenAIAGENTS.md

mcp-extensions

openai/mcp-extensions/AGENTS.md

Use this repository as a reference when building MCP apps and servers.

No other project uses it yet

1.1k37d 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.