AGENTS.md examples from real projects

MicrosoftReads credentialsAGENTS.md

Web-Dev-For-Beginners / nl

microsoft/Web-Dev-For-Beginners/translations/nl/AGENTS.md

your-work/` mappen - Afbeeldingen opgeslagen in les-specifieke `images/` mappen - Vertalingen in `translations/{language-code}/` structuur ## Build en Deployment ### Quiz App Deployment (Azure Static Web Apps) De quiz

MicrosoftReads credentialsAGENTS.md

Web-Dev-For-Beginners / pcm

microsoft/Web-Dev-For-Beginners/translations/pcm/AGENTS.md

description if e get ### Review Process - PRs go through maintainer and community review - Educational clarity dey important - Code examples suppose follow current best practices - Translations go through accuracy and cultural

MicrosoftReads credentialsAGENTS.md

Web-Dev-For-Beginners / ta

microsoft/Web-Dev-For-Beginners/translations/ta/AGENTS.md

start/` அல்லது `your-work/` அடைவுகள் - படங்கள் பாடத்திற்கு தொடர்பான `images/` அடைவுகளில் சேமிக்கப்பட்டவை - மொழிபெயர்ப்புகள் `translations/{language-code}/` கட்டமைப்பில் ## Build and Deployment ### Quiz App Deployment (Azure Static Web Apps) quiz-app Azure Static

MicrosoftReads credentialsAGENTS.md

Web-Dev-For-Beginners / tl

microsoft/Web-Dev-For-Beginners/translations/tl/AGENTS.md

angkop ### Proseso ng Review - Ang mga PR ay sinusuri ng mga maintainer at komunidad - Pinapahalagahan ang kalinawan sa edukasyon - Dapat sundin ng mga halimbawa ng code ang kasalukuyang best practices

MicrosoftReads credentialsAGENTS.md

Web-Dev-For-Beginners / zh-HK

microsoft/Web-Dev-For-Beginners/translations/zh-HK/AGENTS.md

說明中引用編號 ### Review Process - PR 由維護者與社群審查 - 優先考量教育清晰性 - 程式碼範例需符合現行最佳實踐 - 翻譯確認準確且文化適切 ## Translation System ### Automated Translation - 使用 GitHub Actions 及 co-op-translator 工作流程 - 自動翻譯成50多種語言 - 主要檔案位於主目錄 - 翻譯檔案位於 `translations/{language-code}/` 目錄 ### Adding Manual Translation

vllm-projectPipes a download into a shellAGENTS.md

vllm

vllm-project/vllm/AGENTS.md

work. ### Accountability - Pure code-agent PRs are **not allowed**. A human submitter must understand and defend the change end-to-end. - The submitting human must review every changed line

No other project uses it yet

nexu-ioReads credentialsAGENTS.md

open-design

nexu-io/open-design/AGENTS.md

issue-first rule for non-trivial features; `docs/code-review-guidelines.md` is the reviewer-facing complement. ## Code review guide - Use `docs/code-review-guidelines.md` as the repository-wide review standard. That document is the operational guide

No other project uses it yet

nexu-ioAGENTS.md

open-design

nexu-io/open-design/.github/AGENTS.md

cross-workflow behavior, update the topology tests instead of relying only on workflow YAML review. ## Architecture GitHub automation uses two layers. Business layer: - Business workflows decide what happened and what

No other project uses it yet

infiniflowAGENTS.md

ragflow

infiniflow/ragflow/AGENTS.md

build.sh --test`; that is expected, not an external service. ## Working Rules - When reviewing documentation or code, inspect the full affected path and report all verifiable findings in one review

louislamAGENTS.md

uptime-kuma

louislam/uptime-kuma/AGENTS.md

programming language), even though it is working. - You use AI to reply to our code review comments. You may use AI tools to understand the codebase and as an assistant

No other project uses it yet

zed-industriesAGENTS.md

zed

zed-industries/zed/docs/AGENTS.md

Summary ### Changes Made | File | Change | Related Code | | -------------- | ----------------- | ----------------- | | path/to/doc.md | Brief description | link to PR/commit | ### Rationale Brief explanation of why these updates were made. ### Review Notes Any items reviewers should pay special

No other project uses it yet

All-Hands-AIAGENTS.md

OpenHands

All-Hands-AI/OpenHands/AGENTS.md

Create TDD tests for behavioral changes. Keep tests focused on user behavior and real code paths: - Use Arrange, Act, Assert structure and clear test data. - Avoid duplicate cases and duplicate

No other project uses it yet

home-assistantPipes a download into a shellAGENTS.md

core

home-assistant/core/AGENTS.md

code quality and maintainability. When looking for examples of something, these are good places to start. The level is indicated in the manifest.json of the integration. - When reviewing entity actions

No other project uses it yet

Model Context ProtocolReads credentialsAGENTS.md

servers

modelcontextprotocol/servers/AGENTS.md

used, not general-purpose products. **This file holds the _rules_: the conventions a reviewer cites against a diff.** It is loaded in full at the start of every session

storybookjsAGENTS.md

storybook

storybookjs/storybook/AGENTS.md

each skill has a symlink in `.claude/skills/`; add one when you add a skill. ## Code Review Before reviewing a pull request or a diff, read [`.agents/guidelines/code-review.md`](.agents/guidelines/code-review.md) and follow

koala73AGENTS.md

worldmonitor

koala73/worldmonitor/AGENTS.md

that PR after relevant review or CI failures. - Keep explicit diagnosis-only requests, standalone code reviews, and pure explanations read-only. Interpret the whole request and the accepted task scope

bytedanceReads credentialsAGENTS.md

deer-flow

bytedance/deer-flow/AGENTS.md

system, test layout. - **[frontend/AGENTS.md](frontend/AGENTS.md)** — frontend depth: Next.js App Router layout, thread/streaming data flow, code style, commands. ## What is DeerFlow DeerFlow combines LangGraph and Next.js with thread-isolated sandbox execution

bytedanceReads credentialsAGENTS.md

deer-flow / frontend

bytedance/deer-flow/frontend/AGENTS.md

uses `[...value.trim()].length`, matching Pydantic; do not use HTML `maxLength`, which counts UTF-16 code units instead. Custom Agent tool access is edited from the configured names returned

bytedanceReads credentialsAGENTS.md

deer-flow / scripts

bytedance/deer-flow/scripts/AGENTS.md

later changes after it is part of the trusted base. Preapproved digests must be code-reviewed in that first change; after the corresponding file revision lands, promote the consumed digest

No other project uses it yet

lobehubReads credentialsAGENTS.md

lobe-chat

lobehub/lobe-chat/AGENTS.md

skill for placement, naming, test location, and how a large file becomes a directory. ### Code Review Before reviewing a PR / diff / branch change, read the **deep-review** skill. Ordinary review