agentleFS
Sign inSign up

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Most stars first · from page 41Worked for most · soon
VercelAGENTS.md

vercel / python

vercel/vercel/python/AGENTS.md

- Dependencies: PEP 440 compatible release clauses (rich ~= 14.0), avoid pinning patch releases (rich ~= 14.0.0). - Only add code that is actually used. No speculative APIs or exports. - _internal/ is private — no backwards compatibility needed when refactoring. - uv: uv sync, uv run <cmd>, uv add <pkg> - ruff: uv run ruff check . (lint), uv run ruff format . (format) - pytest: uv run pytest, uv run pytest tests/testfoo.py, uv run pytest -k testname. Tests…

16k8mo agoDiscuss
HBAI-LtdAGENTS.md

Toonflow-app

HBAI-Ltd/Toonflow-app/AGENTS.md

所有文件操作均返回 Promise;写入、改名、删除、建目录成功时无返回内容。

16k8d agoDiscuss
ag-ui-protocolAGENTS.md

ag-ui

ag-ui-protocol/ag-ui/AGENTS.md

- For requests to add A2UI rendering to AG-UI applications or to scaffold an AG-UI + A2UI quickstart, use skills/ag-ui-a2ui-integration/SKILL.md. - When running tasks (for example build, lint, test, e2e, etc.), always prefer running the task through nx (i.e. nx run, nx run-many, nx affected) instead of using the underlying tooling directly - You have access to the Nx MCP server and its tools, use them to help the user - When answering questions about the repository, use the nxworkspace…

16k7mo agoDiscuss
CloudflareAGENTS.md

cloudflared

cloudflare/cloudflared/AGENTS.md

Cloudflare's command-line tool and networking daemon written in Go. Production-grade tunneling and network connectivity services used by millions of developers and organizations worldwide. Notes on linting: - .golangci.yaml is configured with new-from-rev and whole-files: true. Touching a file triggers linting of the ENTIRE file, not just the changed hunks. Expect to fix pre-existing issues in files you modify, or add targeted // nolint: <linter> comments with a short justification. - Prefer defer func() { _ = resource.Close() }() over defer…

16k21d agoDiscuss
HashiCorpAGENTS.md

packer

hashicorp/packer/AGENTS.md

Packer is HashiCorp's open-source (BUSL-1.1) CLI for building automated machine images. It is a Go program that orchestrates pluggable builders, provisioners, post-processors, and data sources through the hashicorp/packer-plugin-sdk, driven by…

16k3mo agoDiscuss
chenhg5AGENTS.md

cc-connect

chenhg5/cc-connect/AGENTS.md

CC-Connect is a bridge that connects AI coding agents (Claude Code, Codex, Gemini CLI, Cursor, etc.) with messaging platforms (Feishu/Lark, Telegram, Discord, Slack, DingTalk, WeChat Work, QQ, LINE). Users interact…

16k7mo agoDiscuss
YishenTuAGENTS.md

claudian

YishenTu/claudian/AGENTS.md

No summary in the file. Open it to read it.

16k2mo agoReads credentialsDiscuss
YishenTuAGENTS.md

claudian / scripts

YishenTu/claudian/scripts/AGENTS.md

No summary in the file. Open it to read it.

16k2mo agoDiscuss
YishenTuAGENTS.md

claudian / tests

YishenTu/claudian/tests/AGENTS.md

No summary in the file. Open it to read it.

16k2mo agoDiscuss
eigent-aiAGENTS.md

eigent

eigent-ai/eigent/AGENTS.md

Before planning, generating, reviewing, or modifying any user-facing UI, read docs/design-system/design.md completely. Treat it as the active product design contract for all UI work in this repository. Use docs/design-system/index.html as the visual reference. The Markdown guideline remains authoritative when the two formats differ. For UI implementation: 1. Inspect the nearest existing product surface for behavior and layout context. 2. Reuse primitives from src/components/ui before creating a new component. 3. Use the semantic tokens and supported component axes documented in the…

15k6d agoDiscuss
yusufkaraaslanAGENTS.md

Skill_Seekers

yusufkaraaslan/Skill_Seekers/AGENTS.md

Comprehensive reference for AI coding agents. Skill Seekers is a Python CLI tool (v3.6.0) that converts documentation sites, GitHub repos, PDFs, videos, notebooks, wikis, and more into AI-ready skills for 21+ LLM platforms and RAG pipelines. Skill Seekers is a universal preprocessing layer that transforms raw documentation and code into structured knowledge assets. It supports 17+ source types and exports to 21+ AI platforms including Claude, Gemini, OpenAI, LangChain, LlamaIndex, and various vector databases. Note: tests/conftest.py checks that skill_seekers is…

15k12mo agoReads credentialsDiscuss
ElasticAGENTS.md

logstash

elastic/logstash/AGENTS.md

Logstash is a server-side data processing pipeline that ingests data from multiple sources, transforms it, and sends it to various destinations. It's part of the Elastic Stack and is a…

15k6mo agoDiscuss
ElasticAGENTS.md

logstash / qa

elastic/logstash/qa/AGENTS.md

Guidance for coding agents working with the QA test infrastructure. See also the root AGENTS.md for general project conventions. The qa/ directory contains three independent test suites: Each suite has…

15k6mo agoDiscuss
ElasticAGENTS.md

logstash / x-pack

elastic/logstash/x-pack/AGENTS.md

Guidance for coding agents working with X-Pack (Elastic-licensed) features. See also the root AGENTS.md for general project conventions. X-Pack provides commercial features that extend the Logstash core. Most features integrate…

15k6mo agoDiscuss
AgriciDanielAGENTS.md

claude-obsidian

AgriciDaniel/claude-obsidian/AGENTS.md

claude-obsidian is a local-first Agent Skills package for building source-cited, compounding Obsidian knowledge bases. It also ships a Claude Code plugin adapter. The portable workflow is implemented in skills/ and the standard-library claude_obsidian/ core; host hooks never define knowledge behavior. - This repository is the product source. It is not the default user vault. - A user vault is the directory containing .claude-obsidian.json, wiki/, and .raw/. Mutable state always belongs there. - templates/vault/ is the distributable seed. Root wiki/, .raw/,…

15k21d agoDiscuss
MicrosoftAGENTS.md

RD-Agent / claude

microsoft/RD-Agent/rdagent/scenarios/rl/autorl_bench/agents/claude/AGENTS.md

You MUST maintain a file called summary.md in the workspace root. Update it after every training attempt and every submission, not just at the end.

15k7mo agoDiscuss
NanmiCoderAGENTS.md

cc-haha / adapters

NanmiCoder/cc-haha/adapters/AGENTS.md

These rules apply to adapters/ changes in addition to the root instructions.

15k4d agoDiscuss
NanmiCoderAGENTS.md

cc-haha

NanmiCoder/cc-haha/AGENTS.md

This is a routing guide for coding agents. Keep shared instructions model-independent; put task-specific detail next to the code or in the linked guides. Rules closer to the code take precedence. For the directory you are changing, read the nested AGENTS.md in that directory and any applicable ancestors. Load other documentation when the task needs it.

15k4d agoDiscuss
NanmiCoderAGENTS.md

cc-haha / desktop

NanmiCoder/cc-haha/desktop/AGENTS.md

These rules apply to desktop/ changes in addition to the root instructions.

15k4d agoDiscuss
NanmiCoderAGENTS.md

cc-haha

NanmiCoder/cc-haha/docs/AGENTS.md

These rules apply to docs/ changes in addition to the root instructions. Two audiences, nothing else. If a page serves neither, it does not belong here. Internal process artefacts (migration task lists, validation checklists, design proposals, release runbooks) are not documentation. Keep them out of docs/, or fold the durable part into internals/contributing.md. Six top-level sections: start/, cases/, desktop/, im/, cli/, internals/. Register any added section in the sections array of site/scripts/generate-docs-manifest.mjs. docs/en/ mirrors the Chinese tree file for file.…

15k4d agoDiscuss
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.