plugins / zoom
openai/plugins/plugins/zoom/AGENTS.md
This repository contains the Zoom plugin for Codex. Its purpose is to help users and engineers:
How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
openai/plugins/plugins/zoom/AGENTS.md
This repository contains the Zoom plugin for Codex. Its purpose is to help users and engineers:
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/pymodule.rs defines using pyo3 what functions are exposed to the python version of the library with a wrapper in python/openaiharmony/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…
openai/openai-agents-js/AGENTS.md
This guide helps new contributors get started with the OpenAI Agents JS monorepo. It covers repo structure, how to test your work, available utilities, file locations, and guidelines for commits and PRs. Location: AGENTS.md at the repository root. Follow SECURITY.md for repository scope and private vulnerability reporting, and CONTRIBUTING.md for contributor security practices. These requirements guide work; their presence does not prove that GitHub or registry controls are configured or that a security scan has completed.
openai/openai-go/AGENTS.md
Most SDK source is generated by Castiron. Follow CONTRIBUTING.md before changing generated files. Handwritten policy, automation, tests, and examples should remain small and should not alter exported SDK APIs unless the change explicitly requires it. Follow the custom-code guidance. Budget changes belong in a separate PR containing only .castiron-ratchet.json, with an explicit justification in the PR description. Increases require a human approving review before merging. Agents may investigate and draft proposals, but must not approve budget increases (including through a…
openai/openai-openapi/AGENTS.md
Read the contribution policy before working here. Everyone can contribute through issues; pull requests are limited to OpenAI team members. External contributors should use the README's feedback process instead.
openai/openai-java/AGENTS.md
Read CONTRIBUTING.md and SECURITY.md before making changes. Most SDK sources are generated; .castiron.stats.yml records generation metadata. Check whether the generator owns the code you are changing, preserve existing generated behavior, and update the authoritative source when it is available. The openai-java-example/ directory is not modified by the generator. Follow the custom-code guidance. Budget changes belong in a separate PR containing only .castiron-ratchet.json, with an explicit justification in the PR description. Increases require a human approving review before merging. Agents may…
openai/apps-sdk-ui/AGENTS.md
Apps SDK UI is a design system tailored for building apps in ChatGPT. Apps SDK UI provides styling foundations, CSS variable design tokens, and a library of well-crafted, accessible components. Keep this goal and context in mind as you contribute code to the repository. This code is the foundation for many other projects, and changes should be robust, well-considered, and workable for many different contexts. You should make changes only in the src/ folder: When adding new functionality or docs,…
openai/realtime-voice-component/AGENTS.md
No summary in the file. Open it to read it.
openai/realtime-voice-component/demo/AGENTS.md
This demo/ app is organized as a small set of canonical examples for the package, not as a general-purpose sandbox. Run these when you change the demo app:
openai/build-hours/18-responses-api/openai-simulator/AGENTS.md
Keep the UX snappy: conversations should feel like texting with a coach. Preserve the last-two-message window and streaming feel whenever you touch dialogue logic.
openai/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.
openai/openai-cli/AGENTS.md
Read CONTRIBUTING.md and SECURITY.md before making changes. Most files in pkg/cmd/ are generated from the OpenAPI specification by Castiron. Generated files identify themselves with a File generated header; .castiron.stats.yml and api_reference/openapi.transformed.yml record the generation inputs. Establish whether the generator owns a file before editing it. Fix recurring generated defects in the authoritative schema or generator when available instead of introducing broad manual changes. Handwritten CLI behavior lives in pkg/custom/; API response selection and reshaping live in pkg/transformers/. Use cohesive internal/…
openai/openai-chatkit-advanced-samples/agents.md
This document explains how to customize the ChatKit starter template that lives in this repository. It covers the React client wrapper, the server-side integration that powers agent responses, and the…
openai/role-specific-plugins/plugins/data-analytics/AGENTS.md
This plugin contains a complex fullscreen analytics artifact workspace plus compact inline chart and table widgets. Preserve that architecture when iterating: artifacts are snapshot-first workspaces, while chart and table widgets are focused views of reviewed query results. Follow the local Codex style contract in src/codex-style-contract.md. src/styles/codex-theme.css is the copied Codex fallback baseline and must load before src/analytics-app/tokens.css. Shared surfaces, controls, typography, spacing, borders, radii, shadows, focus, and motion should resolve through the Codex tokens. Analytics CSS may extend the baseline…
openai/role-specific-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 substantial visual changes, use the Product Design plugin's get-context skill when the visual source is unclear or no longer matches the current goal. When the user gives durable prototype-specific design feedback, preferences, or decisions, record them in AGENTS.md. When implementing from a selected generated mock, treat that image as the…
openai/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",…
openai/openai-ruby/AGENTS.md
- Use the examples: Conventional Commit prefix for changes whose primary purpose is updating or fixing examples, including their dedicated tests. Apply the same prefix to pull request titles; do not use fix: or fix(examples): for these changes. - Choose Conventional Commit prefixes based on user impact. Reserve fix: for changes that materially change the shipped gem's behavior in a way that impacts users. CI-only, workflow-only, build/test infrastructure, and repository-maintenance changes should use an appropriate non-user-facing prefix such as ci:.…
openai/imagegencam/AGENTS.md
This repo is designed to be opened directly in Codex Desktop. Do not ask users to install a separate Codex skill. - Act like the tutorial guide, not like a docs search engine. The user should feel that Codex took over after they pasted the README prompt. - Guide one step at a time. - Do not dump a full build plan unless the user asks for one. Give the next concrete action, wait for the user to do the…
openai/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…
openai/euphony/agents.md
No summary in the file. Open it to read it.
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.