How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
VercelAGENTS.mdvercel-labs/agent-skills/skills/react-native-skills/AGENTS.md
Version 1.0.0 Engineering January 2026 Note: This document is mainly for agents and LLMs to follow when maintaining, generating, or refactoring React Native codebases. Humans may also find it useful,…
VercelAGENTS.mdvercel-labs/agent-skills/skills/react-view-transitions/AGENTS.md
Version 1.0.0 Vercel Engineering Note: This standalone guide is compiled from SKILL.md and its reference files for agents that consume a single AGENTS.md document. Edit the source files, not this…
VercelAGENTS.mdvercel-labs/agent-skills/skills/vercel-optimize/AGENTS.md
Cross-agent entry point for the Vercel Optimize skill. The full procedure is in SKILL.md. Use this skill when the user asks to optimize a Vercel project, reduce a Vercel bill,…
VercelAGENTS.mdvercel/turborepo/AGENTS.md
PR titles must follow Conventional Commits. See .github/workflows/lint-pr-title.yml for the enforced constraints. Format: <type>: <Description> Turborepo configuration, task behavior, and CLI commands can vary between installed versions and may differ from your training data. Resolve the turbo package from this file's directory or relevant workspace; in monorepos, it may not be visible from the repository root. For example, run node -p "require.resolve('turbo/package.json')" from a workspace that depends on turbo. Read docs/README.md inside that installed package first, then read the relevant…
VercelAGENTS.mdvercel/turborepo/apps/docs/AGENTS.md
The root AGENTS.md also applies to this app. Geistdocs owns shared runtime behavior, while this app owns Turborepo content, routes, metadata, assets, and adapters. This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before writing any code. Heed deprecation notices. This block is written and re-added by…
VercelAGENTS.mdvercel/turborepo/examples/basic/AGENTS.md
Turborepo configuration, task behavior, and CLI commands can vary between installed versions and may differ from your training data. Resolve the turbo package from this file's directory or relevant workspace; in monorepos, it may not be visible from the repository root. For example, run node -p "require.resolve('turbo/package.json')" from a workspace that depends on turbo. Read docs/README.md inside that installed package first, then read the relevant pages from its docs/ directory before changing Turborepo configuration or commands. Heed deprecation notices. These…
VercelAGENTS.mdvercel/turborepo/examples/with-nextjs-elysia/apps/web/AGENTS.md
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ before writing any code. Heed deprecation notices. <!-- END:nextjs-agent-rules -->
topoteretesAGENTS.mdtopoteretes/cognee/AGENTS.md
This document summarizes how to work with the cognee repository: how it’s organized, how to build, test, lint, and contribute. It mirrors our actual tooling and CI while providing quick commands for local development. Notes: - Co-locate feature-specific helpers under their respective package (modules/, infrastructure/, or tasks/). - Extend the system by adding new tasks, loaders, or retrievers rather than modifying core pipeline mechanisms. Python (root) – requires Python >= 3.10 and < 3.15 (i.e. 3.10–3.14, see pyproject.toml). We recommend…
googleworkspaceAGENTS.mdgoogleworkspace/cli/AGENTS.md
gws is a Rust CLI tool for interacting with Google Workspace APIs. It dynamically generates its command surface at runtime by parsing Google Discovery Service JSON documents. [!IMPORTANT] Dynamic Discovery: This project does NOT use generated Rust crates (e.g., google-drive3) for API interaction. Instead, it fetches the Discovery JSON at runtime and builds clap commands dynamically. When adding a new service, you only need to register it in crates/google-workspace/src/services.rs and verify the Discovery URL pattern in crates/google-workspace/src/discovery.rs. Do NOT add…
ComposioHQAGENTS.mdComposioHQ/composio/AGENTS.md
Repository guidance for Codex, Claude Code, Cursor, pi.dev, and other AI coding agents. This is the Composio SDK v3 monorepo. Most product code lives in ts/ and python/; docs live in docs/. Branch new work from next and target PRs at next unless the user says otherwise. Follow the Contribution Policy in CONTRIBUTING.md. When helping an author prepare a PR: Use the smallest relevant skill: Do not hand-edit these. They are regenerated or vendored, and edits will be overwritten. They…
ComposioHQAGENTS.mdComposioHQ/composio/docs/AGENTS.md
Documentation-site guidance for AI agents working under docs/. docs/ is a Fumadocs/Next.js site. Docs PRs branch from next and target next. Run commands from docs/:
ComposioHQAGENTS.mdComposioHQ/composio/python/AGENTS.md
Python SDK guidance for AI agents. python/ contains the Python SDK, provider packages, tests, nox sessions, release scripts, and Python docs. Run from python/: Every field of an API response is untrusted input — including slugs, IDs, and filenames. The SDK's threat model assumes the backend may be compromised or the connection MITM'd, and that a third-party toolkit can return anything. When untrusted directory components such as slugs or IDs become part of a filesystem path, use composio.utils.safepath.securejoin(root, *components). For…
ComposioHQAGENTS.mdComposioHQ/composio/ts/AGENTS.md
TypeScript workspace guidance for AI agents. ts/ contains the TypeScript SDK packages, examples, CLI, and runtime E2E tests. Run from the repository root:
decoluaAGENTS.mddecolua/9router/open-sse/AGENTS.md
Provider-agnostic SSE engine: one OpenAI-style request → any provider (LLM chat, image, embedding, tts, stt, search), streamed back in the client's format. handlers/chatCore.js → services/model.js parseModel (resolve provider/model) → RTK for cursor (rtk/ compresses the source-format tool_result / role:tool in-place — its translator rewrites those shapes, so this one provider must run before translate) → translator/index.js translateRequest (client format → provider format) → post-translate savers (rtk/ compress for every other provider, rtk/headroom.js proxy compress, rtk/caveman.js / rtk/ponytail.js system inject —…
oraiosAGENTS.mdoraios/serena/AGENTS.md
This project uses Serena for development. Make sure that you read the project's critical_info memory before working on it. * When using Serena, the memory is provided either - along…
LangChainAGENTS.mdlangchain-ai/deepagents/AGENTS.md
This file contains repository-wide rules for agents and contributors. Use these sources for details instead of duplicating them here: 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. Work inside the package you are changing; libs/DEVELOPMENT.md covers environment setup (uv, make) and the edit-test-lint loop. Do not add dependencies unless required. When adding one, justify its maintenance, adoption, and release…
LangChainAGENTS.mdlangchain-ai/deepagents/examples/content-builder-agent/AGENTS.md
You are a content writer for a technology company. Your job is to create engaging, informative content that educates readers about AI, software development, and emerging technologies. Our content focuses on: - AI agents and automation - Developer tools and productivity - Software architecture and best practices - Emerging technologies and trends Before writing on any topic: 1. Use the researcher subagent for in-depth topic research 2. Gather at least 3 credible sources 3. Identify the key points readers need…
LangChainAGENTS.mdlangchain-ai/deepagents/examples/deploy-coding-agent/AGENTS.md
You are an expert software engineer that solves coding tasks autonomously. You work inside a sandboxed environment with full shell access. Follow this phased workflow for every task: For complex tasks, delegate to subagents: - Use task(subagenttype="researcher") for researching APIs, docs, or patterns - Use task(subagenttype="general-purpose") for independent subtasks
LangChainAGENTS.mdlangchain-ai/deepagents/examples/deploy-content-writer/AGENTS.md
You are a content writer for a technology company. Your job is to create engaging, informative content that educates readers about AI, software development, and emerging technologies. You have access to per-user memory files at /memories/user/. Use ls /memories/user/ to discover available files. Always read your user memory files before starting work. When the user shares preferences, update /memories/user/preferences.md using edit_file.
LangChainAGENTS.mdlangchain-ai/deepagents/examples/deploy-content-writer/user/AGENTS.md
No preferences set yet. The agent will update this file as it learns about the user's preferred topics, tone adjustments, and formatting choices.
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.
