AGENTS.md examples from real projects

langgeniusAGENTS.md

dify / dify-agent

langgenius/dify/dify-agent/AGENTS.md

agent/`: - Lint: `make check` - Format and fix lint: `make fix` - Type check: `make typecheck` - Tests: `make test` Use the package's `uv` environment and Pydantic v2 APIs. Inspect current dependency

langgeniusAGENTS.md

dify / e2e

langgenius/dify/e2e/AGENTS.md

when a required fixture is missing. ## Browser, API, And Contract Boundaries The action under test belongs to the browser. APIs may prepare fixtures, poll persistence, and clean up; they

langgeniusAGENTS.md

dify / web

langgenius/dify/web/AGENTS.md

port. Switch to the Next.js development server (`pnpm -C web dev:next`) only when testing Next.js-specific functionality or investigating behavior that differs from Next.js. - Read `docs/test.md` only for frontend

langflow-aiAGENTS.md

langflow

langflow-ai/langflow/AGENTS.md

make format_frontend # Format TypeScript (biome) make format # Both make lint # mypy type checking ``` ### Testing ```bash make unit_tests # Backend unit tests (pytest, parallel) make unit_tests async=false # Sequential

No other project uses it yet

clash-verge-revAGENTS.md

clash-verge-rev

clash-verge-rev/clash-verge-rev/AGENTS.md

your own words, and verify the change against the reported behavior before submitting. 4. **Tests are justified, not default.** Do not add tests, test scaffolding, or speculative defensive code unless

No other project uses it yet

LangChainReads credentialsAGENTS.md

langchain

langchain-ai/langchain/AGENTS.md

support │ │ └── ... (other integrations maintained by the LangChain team) │ ├── text-splitters/ # Document chunking utilities │ ├── standard-tests/ # Shared test suite for integrations │ └── model-profiles/ # Model configuration profiles ├── .github/ # CI/CD workflows and templates

No other project uses it yet

GitHubAGENTS.md

spec-kit

github/spec-kit/AGENTS.md

operation boundary, command-module naming, private phases, nested command groups, registration ownership, and mirrored tests. ## Adding or Updating MCP Commands Before adding or changing MCP tools for Specify commands, read

No other project uses it yet

comfyanonymousAGENTS.md

ComfyUI

comfyanonymous/ComfyUI/AGENTS.md

blue eyes. Feel free to use her in ComfyUI materials, UI text, examples, tests, generated assets, or comments, but do not disrespect her. - Warning and info messages should be short

VercelReads credentialsAGENTS.md

next.js

vercel/next.js/AGENTS.md

packages ├── turbopack/ # Turbopack bundler (Rust) - git subtree ├── crates/ # Rust crates for Next.js SWC bindings ├── test/ # All test suites ├── examples/ # Example Next.js applications ├── docs/ # Documentation └── scripts/ # Build and maintenance scripts ``` ### Core

VercelAGENTS.md

next.js / test

vercel/next.js/test/AGENTS.md

Test review instructions - During code review, flag any change that newly disables, skips, or omits deploy-mode tests or assertions, including `skipDeployment: true` and `isNextDeploy` conditionals. Only allow this when

yangshunAGENTS.md

tech-interview-handbook

yangshun/tech-interview-handbook/AGENTS.md

check - Run format, lint, and TypeScript type checks - lint - Lint code - fmt - Format code - test - Run tests ### Execute - run - Run monorepo tasks - exec - Execute a command from local `node_modules/.bin

MicrosoftAGENTS.md

PowerToys

microsoft/PowerToys/AGENTS.md

Top-level AI contributor guidance for developing PowerToys - a collection of Windows productivity utilities

garrytanReads credentialsAGENTS.md

gstack

garrytan/gstack/AGENTS.md

star product in the request. | | `/plan-eng-review` | Lock architecture, data flow, edge cases, and tests. | | `/plan-design-review` | Rate each design dimension 0-10, explain what a 10 looks like. | | `/plan-devex-review` | DX-mode

ggml-orgAGENTS.md

llama.cpp

ggml-org/llama.cpp/AGENTS.md

merged. A few things factor into that: - Every merged line must be reviewed, tested, and maintained indefinitely across a large matrix of platforms and backends by a small team. - llama.cpp

No other project uses it yet

OpenAIAGENTS.md

codex / code-mode-host

openai/codex/codex-rs/code-mode-host/AGENTS.md

Tests Do not use timeouts or sleeps to synchronize tests. Wait for explicit signals or observable state; let the test runner enforce test-case timeouts

kubernetesAGENTS.md

kubernetes

kubernetes/kubernetes/AGENTS.md

header from `hack/boilerplate/boilerplate.go.txt`. ## Contributor Guidelines - Keep changes focused and reviewable - Add or update relevant tests. Do not add trivial unit tests just for the sake of code coverage. - When creating

No other project uses it yet

rustdeskAGENTS.md

rustdesk

rustdesk/rustdesk/AGENTS.md

flutter/lib/mobile/` - Shared: `flutter/lib/common/` and `flutter/lib/models/` ## Rust Rules * Avoid `unwrap()` / `expect()` in production code. * Exceptions: * tests; * lock acquisition where failure means poisoning, not normal control flow. * Otherwise prefer `Result` + `?` or explicit

No other project uses it yet

facebookAGENTS.md

react-native

facebook/react-native/AGENTS.md

runtime (Kotlin, Java, JNI) | | `packages/react-native/{React,ReactApple}` | Apple runtime (Objective-C++, Swift) | | `packages/rn-tester` | RNTester — test app showcasing each core component and API, plus a `Playground` scratch surface | | `packages/*` | Other published

reactAGENTS.md

react-native

react/react-native/AGENTS.md

runtime (Kotlin, Java, JNI) | | `packages/react-native/{React,ReactApple}` | Apple runtime (Objective-C++, Swift) | | `packages/rn-tester` | RNTester — test app showcasing each core component and API, plus a `Playground` scratch surface | | `packages/*` | Other published

MicrosoftAGENTS.md

v8-jsi / nodejs

microsoft/v8-jsi/deps/nodejs/AGENTS.md

message-guidelines). The human contributor opening the PR takes full responsibility for the changes. * **Testing and verification**: All changes must pass the Node.js continuous integration. Human judgment must verify that

No other project uses it yet