One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
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.
OpenAIAGENTS.mdopenai/build-hours/22-chatgptapp-pingpong/AGENTS.md
Always use the OpenAI developer documentation MCP server if you need to work with the OpenAI API, ChatGPT Apps SDK, Codex, without me having to explicitly ask.
OpenAISkillopenai/build-hours/24-api-codex/skills/agentic-legibility/SKILL.md
Score a repository's agentic legibility from repo-visible evidence only. Use when Codex needs to audit how easy a codebase is for coding agents to discover, bootstrap, validate, and navigate, especially for harness-engineering reviews, developer-experience audits, repo cleanup, or before/after comparisons after improving docs, tooling, or architectural constraints.
OpenAIAGENTS.mdopenai/tunnel-client/plugins/tunnel-mcp/AGENTS.md
- This api/tunnel-client/plugins/tunnel-mcp path is the public-safe plugin copy mirrored into the standalone openai/tunnel-client repo and exported by tunnel-client codex plugin export. - Do not add internal package-manager wording, internal-repo install wording, or internal marketplace/install references in this path. - Keep user-facing install and upgrade docs in README.md easy to follow from this repository root and from a standalone tunnel-client checkout. - Avoid referring to the larger repository structure in user-facing plugin installation instructions. Use terms like "this repository root",…
OpenAISkillopenai/tunnel-client/plugins/tunnel-mcp/skills/tunnel-mcp/SKILL.md
Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin. Use when Codex needs to manage secure MCP tunnels with aliases and native tunnel-client runtime processes.
OpenAIAGENTS.mdopenai/openai-ruby/AGENTS.md
Prefer direct calls over send, __send__, or public_send for internal plumbing. Cross-component internal methods should remain public for direct dispatch, marked @api private; match RBI/RBS visibility. Preserve x-release-please markers around the local openai version when regenerating gemfiles/bedrock.gemfile.lock; Bundler can remove them. See Running tests for the Bedrock bundle workflow. Follow Generated-file ownership before editing SDK files. Apply CONTRIBUTING's security requirements for secrets/fixtures, diagnostic redaction (including tokens), dependency review, CI/publishing protections, @openai/sdks-team review, and focused regression/security tests. Dependency review includes docs/Gemfile…
OpenAISkillopenai/openai-ruby/.agents/skills/improve-openai-ruby/SKILL.md
Investigate customer-impacting OpenAI Ruby SDK defects and privately handled security risks, then dispatch at most five evidenced, independent fixes to isolated project worktrees.
OpenAIAGENTS.mdopenai/GABRIEL/AGENTS.md
This is the canonical operating guide for coding agents working in this checkout or writing code that uses GABRIEL. Keep it concise and update it when public behavior changes. The README explains the package; the tutorial notebook contains runnable examples; src/gabriel/api.py is the source of truth for public signatures. The recommendations below are practical heuristics, not universal rules. They reflect recurring successful workflows and package behavior at the date shown; they may be stale, unavailable in a particular organization, too…
OpenAIAGENTS.mdopenai/euphony/agents.md
No summary in the file. Open it to read it.
OpenAIAGENTS.mdopenai/openai-guardrails-python/AGENTS.md
Before pushing or opening a pull request, review the complete diff for security impact alongside the normal code review. For affected paths: - Trace untrusted configuration, provider responses, tool arguments, and evaluation inputs to network, file, subprocess, and deserialization operations; verify the trust boundary before side effects. - Check that credentials, prompts, model outputs, and tool data cannot leak through logs, exception chains, telemetry, or test artifacts. Use synthetic regression cases and keep tests hermetic. - Review dependency changes for…
OpenAISkillopenai/openai-guardrails-python/.agents/skills/final-release-review/SKILL.md
Review an openai-guardrails-python release plan or final release candidate against the previous remote tag, determine the compatible release type, audit runtime and packaging risk, inspect current CI, and produce an English ship-or-block report. Use for pre-release readiness checks, not ordinary PR review or implementation.
OpenAISkillopenai/openai-guardrails-python/.agents/skills/implementation-final-review/SKILL.md
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and tests before final verification.
OpenAISkillopenai/openai-guardrails-python/.agents/skills/implementation-kickoff/SKILL.md
Start and carry an explicitly invoked openai-guardrails-python implementation through a fresh isolated worktree and a local PR-ready handoff. Fetch the latest origin/main, keep task changes uncommitted, replay them onto the latest main before final review, run applicable verification and $implementation-final-review, use $pr-draft-summary to generate the complete PR draft and branch name, then create one clean local commit with takeover provenance when applicable. Use only when the user explicitly invokes this skill; never push, open a PR, or mutate GitHub.
OpenAISkillopenai/openai-guardrails-python/.agents/skills/implementation-strategy/SKILL.md
Choose compatibility-aware scope for runtime and API changes in openai-guardrails-python. Use before initial implementation and each review-feedback batch to decide whether to patch, reset the design, preserve compatibility, or reject unsupported cases.
OpenAISkillopenai/openai-guardrails-python/.agents/skills/maintainer-review/SKILL.md
Assess an openai-guardrails-python GitHub issue or pull request as a maintainer. Use to verify the claimed need and practical impact, compare supported alternatives or competing approaches, separate code quality from repository readiness, recommend the maintainer action, and draft a copy-ready comment when evidence, changes, or closure should be requested.
OpenAISkillopenai/openai-guardrails-python/.agents/skills/pr-draft-summary/SKILL.md
Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-guardrails-python after runtime, tests, examples, build/test configuration, or behavior-impacting docs change.
OpenAIAGENTS.mdopenai/snap-o/AGENTS.md
Snap-O is a public, open-source Android inspection tool. Use synthetic data in tests and examples. Never publish credentials, captured private traffic, confidential implementation details, or private issue-tracker links, identifiers, or content. Review the full diff, commit message, and PR text for sensitive information before publishing. Follow release/README.md when changing protocols, published APIs, version metadata, or packaging. Update release/ checks and tests when protocol definitions or source paths change. Use plain technical English in all prose, including READMEs, docs, code comments,…
OpenAIAGENTS.mdopenai/snap-o/app-macos/AGENTS.md
For automated contributors:
OpenAISkillopenai/snap-o/skills/snap-o-network-inspector/SKILL.md
Inspect Android network captures and intercept HTTP calls with the Snap-O CLI for a selected device/socket. Use for request/response details, websocket events, API response overrides, mock responses, or delays with Python route handlers.
OpenAISkillopenai/snap-o/skills/snap-o-tweaks/SKILL.md
Inspect, stream, and explicitly adjust live Android UI tweak values or invoke app-owned actions through Snap-O. Use when a request mentions Snap-O Tweaks, tweak-enabled Android apps, runtime UI parameters, Compose tweak or action controls, tweak discovery, previously adjusted or currently inactive tweaks, applying all user-made tweak changes, typed values, defaults or resets, tweak batches, explicitly registered actions, the Tweaks REST/SSE API, or selecting between CLI, macOS tool, in-app overlay, and custom tweak interfaces.
OpenAIAGENTS.mdopenai/snap-o/tools/AGENTS.md
This is the code repository for the Snap-O macOS app and optional Android libraries to help provide data to Snap-O.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
