How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
JetBrainsAGENTS.mdJetBrains/kotlin/compiler/AGENTS.md
Consider reading fir-basics.md. FIR processes code through sequential phases (see FirResolvePhase.kt). Key invariant: In phase B following phase A, all FIR elements visible in B are resolved to phase A.
router-for-meAGENTS.mdrouter-for-me/CLIProxyAPI/AGENTS.md
Go 1.26+ proxy server providing OpenAI/Gemini/Claude/Codex compatible APIs with OAuth and round-robin load balancing.
ChromeDevToolsAGENTS.mdChromeDevTools/chrome-devtools-mcp/AGENTS.md
This repository contains an MCP server and CLI for Chrome DevTools.
bladerAGENTS.mdblader/humanizer/AGENTS.md
This file explains how to change Humanizer without breaking its package or prompt. Humanizer is an agent skill written in Markdown. SKILL.md is the prompt that agents read. The repo has no build step. Keep the skill portable. Do not write instructions that limit it to one or two agent tools. Keep SKILL.md and README.md in sync. Use Plain Language in code comments, prompts, documentation, descriptions, validation messages, and progress reports.
PydanticAGENTS.mdpydantic/monty/AGENTS.md
No summary in the file. Open it to read it.
CherryHQAGENTS.mdCherryHQ/cherry-studio/.agents/skills/vercel-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…
coreyhaines31AGENTS.mdcoreyhaines31/marketingskills/AGENTS.md
Guidelines for AI agents working in this repository. This repository contains Agent Skills for AI agents following the Agent Skills specification. Skills install to .agents/skills/ (the cross-agent standard). This repo also serves as a Claude Code plugin marketplace via .claude-plugin/marketplace.json. Skills are content-only (no build step). Verify manually: - YAML frontmatter is valid - name field matches directory name exactly - name is 1-64 chars, lowercase alphanumeric and hyphens only - description is 1-1024 characters CLI tools (tools/clis/*.js) are zero-dependency…
AstralAGENTS.mdastral-sh/ruff/AGENTS.md
This repository contains both Ruff (a Python linter and formatter) and ty (a Python type checker). The crates follow a naming convention: ruff* for Ruff-specific code and ty* for ty-specific code. ty reuses several Ruff crates, including the Python parser (ruffpythonparser) and AST definitions (ruffpythonast). Before starting work on an issue and again before opening a pull request, follow the guidance on avoiding duplicate work. If an open pull request already addresses the issue, do not submit a competing one…
ayghriAGENTS.mdayghri/i-have-adhd/AGENTS.md
This file is the map for agents working with i-have-adhd. Read it after locating or installing the repository. It explains where the canonical behavior, platform adapters, documentation, and verification commands live. It does not replace the skill rules in skills/i-have-adhd/SKILL.md. Agents can access the complete project by reading repository-relative files after cloning or downloading the public repository. Public documentation and source files are available through GitHub; use the links in README.md and INSTALL.md to find translated documentation and platform instructions.…
QuantumNousAGENTS.mdQuantumNous/new-api/AGENTS.md
DO NOT send optional commentary This is an AI API gateway/proxy built with Go. It aggregates 40+ upstream AI providers (OpenAI, Claude, Gemini, Azure, AWS Bedrock, etc.) behind a unified…
QuantumNousAGENTS.mdQuantumNous/new-api/web/AGENTS.md
本文档定义前端项目的开发规范与最佳实践，供开发与 AI 助手共同遵循。具体依赖与脚本以 package.json 为准。 优先复用项目已有组件与能力（见 3.3 组件）；项目内无合适实现时，再评估已安装依赖及成熟、维护良好的开源库。仅在复用、组合或合理扩展仍无法满足需求时自行实现，并说明具体能力缺口。 - 枚举与文案（常量中的 i18n） 各 feature 的 constants.ts 中常出现「枚举/状态 + 展示文案」或「成功/错误消息」，须统一约定以免遗漏 i18n、用法混乱： - 成功/错误/提示类消息（如 SUCCESSMESSAGES、ERRORMESSAGES）：常量值仅表示 i18n 键（与英文 fallback 同字面量）。展示时必须通过 t() 使用，例如 toast.success(t(SUCCESSMESSAGES.APIKEYCREATED))、toast.error(t(ERRORMESSAGES.UNEXPECTED))，禁止直接 toast.success(SUCCESS_MESSAGES.xxx)…
HKUDSAGENTS.mdHKUDS/nanobot/AGENTS.md
This file provides guidance to AI coding agents working with this repository. nanobot is a lightweight, open-source AI agent framework written in Python with a React/TypeScript WebUI. It centers around a small agent loop that receives messages from chat channels, invokes an LLM provider, executes tools, and manages session memory. Messages flow through an async MessageBus (nanobot/bus/queue.py) that decouples chat channels from the agent core:
jeecgbootAGENTS.mdjeecgboot/JeecgBoot/jeecgboot-vue3/AGENTS.md
This file provides repository guidance for Codex when working in this project. JeecgBoot Vue3 (v3.8.3) is an enterprise low-code admin platform frontend. It is built on Vue 3, TypeScript, Vite, Ant Design Vue 4, and Pinia. It was originally forked from Vben Admin and customized with JeecgBoot-specific components such as online forms, code generation, workflow, and related low-code modules. This workspace uses SVN for version control. Do not assume Git is available in this directory. Backend: Spring Boot (JeecgBoot), expected…
sickn33AGENTS.mdsickn33/agentic-awesome-skills/AGENTS.md
This repository publishes an installable library of agent skills and plugin bundles. Canonical skill sources live in skills/<skill-id>/SKILL.md; use lowercase, hyphenated skill IDs. Mirrored plugin distributions live under plugins/. Contributor and user docs live in docs/; localized docs live in docszh-CN/ and docs/vietnamese/. Maintenance scripts and tests are in tools/scripts/ and tools/scripts/tests/. The hosted catalog app is in apps/web-app/. Registry outputs such as CATALOG.md, skillsindex.json, and data/catalog.json are generated artifacts. Editorial inputs in data/ remain source files; use tools/scripts/generated_files.js for…
danny-avilaAGENTS.mddanny-avila/LibreChat/AGENTS.md
See CLAUDE.md. Normally branch off dev and target dev; gh pr create defaults to main, so pass --base dev explicitly. main is the released branch, kept as a fast-forward of dev and synced as-is — never open a backport pull request to main, because anything merged to dev reaches it at the next sync. Pull requests opened against main are retargeted automatically. Maintainer-directed canary exception: Experimental work, or a PR ready to merge after review but not yet suitable for…
SentryAGENTS.mdgetsentry/sentry/AGENTS.md
IMPORTANT: AGENTS.md files are the source of truth for AI agent instructions. Always update the relevant AGENTS.md file when adding or modifying agent guidance. Do not add to CLAUDE.md or…
SentryAGENTS.mdgetsentry/sentry/src/AGENTS.md
For critical commands, see the "Command Execution Guide" section in /AGENTS.md in the repository root. Multi-tenant queries MUST be scoped — never trust user-supplied IDs alone. - Always filter by…
SentryAGENTS.mdgetsentry/sentry/src/sentry/issues/derived/AGENTS.md
Follow README.md in this directory when changing Features or aggregators here.
SentryAGENTS.mdgetsentry/sentry/static/AGENTS.md
For critical commands and testing rules, see the "Command Execution Guide" section in /AGENTS.md in the repository root. Use apiOptions with useQuery from TanStack Query; never use the deprecated useApiQuery/getApiQueryData/setApiQueryData.…
SentryAGENTS.mdgetsentry/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),…
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.
