How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
LangChainAGENTS.mdlangchain-ai/deepagents/examples/deploy-coding-agent/AGENTS.md
your plan step by step - Write clean, idiomatic code that matches existing patterns - Run tests after each significant change - If tests fail, debug and fix before moving on - Update your
LangChainAGENTS.mdlangchain-ai/deepagents/libs/code/AGENTS.md
skills, sandbox bootstrap, and slash-command surface. For monorepo-wide conventions (commit titles, lint, testing, docs, CI, benchmarks), see the root `AGENTS.md`. For a high-level map of the package
LangChainAGENTS.mdlangchain-ai/deepagents/libs/evals/AGENTS.md
aggregate-only`. - `pytest_reporter` rewrites pytest's session exit status to `0` even when tests fail, so `pytest_returncode` is not a reliable failure signal — use `counts.failed.mean` instead. Per-trial
LangChainAGENTS.mdlangchain-ai/deepagents/libs/partners/AGENTS.md
name. Each partner package is independently versioned and owns its environment, `pyproject.toml`, `Makefile`, and tests. ## Adding a partner package Wire a new partner into all relevant repository surfaces: - Area options
labringAGENTS.mdlabring/FastGPT/AGENTS.md
关键目录 - `document/` - 文档站点(NextJS 应用及内容) - `plugins/` - 外部插件(模型、爬虫等) - `deploy/` - Docker 和 Helm 部署配置 - `test/` - 集中的测试文件和工具 ## 开发命令 常用开发命令见 [FastGPT 开发命令](./.agents/code/commands.md)。 ## 测试 项目使用 Vitest 进行测试并生成覆盖率报告。主要测试命令: - `pnpm test` - 运行所有测试 - `pnpm
OpenAIAGENTS.mdopenai/openai-agents-python/AGENTS.md
real credentials, customer data, private prompts or responses, tool payloads, or recordings in code, tests, snapshots, logs, documentation, or shared artifacts. Use approved credential injection only for explicitly authorized live
Hugging FaceAGENTS.mdhuggingface/smolagents/AGENTS.md
Follow OOP principles - Be Pythonic: follow Python best practices and idiomatic patterns - Write unit tests for new functionality
alibabaAGENTS.mdalibaba/page-agent/AGENTS.md
Build and zip the extension package npm run typecheck # Typecheck all packages npm run test # Run unit tests across all workspaces npm run lint # ESLint ``` ## Architecture ### Monorepo Structure Source-first
rohitg00AGENTS.mdrohitg00/agentmemory/AGENTS.md
engine's StateModule (`./data/state_store.db`) - **Build**: TypeScript → ESM via tsdown, output to `dist/` - **Test**: vitest (`npm test` excludes integration tests) ## Consistency Rules **When adding or removing MCP tools, you MUST update
MongoDBAGENTS.mdmongodb/mongo/jstests/AGENTS.md
JavaScript Test Code Conventions ### Assertion Library ALWAYS use our own assertion library that is defined at `src/mongo/shell/assert.js` and automatically loaded into the global scope before running each test. ALWAYS wrap
kestra-ioAGENTS.mdkestra-io/kestra/AGENTS.md
color, spacing, radius or component pattern may be invented in feature code. - **A test has to be able to fail for a reason a reviewer would care about**: see [When
BloopAIAGENTS.mdBloopAI/vibe-kanban/AGENTS.md
types` Do not manually edit shared/remote-types.ts, instead edit crates/remote/src/bin/remote-generate-types.rs (see crates/remote/AGENTS.md for details). ## Build, Test, and Development Commands - Install: `pnpm i` - Run dev (web app + backend with ports auto-assigned
BloopAIAGENTS.mdBloopAI/vibe-kanban/docs/AGENTS.md
realistic data instead of placeholder values - Include expected outputs and results for verification - Test all code examples thoroughly before publishing - Specify language and include filename when relevant - Add explanatory comments
Hugging FaceAGENTS.mdhuggingface/lerobot/AGENTS.md
package management) ## Development Setup ```bash uv sync --locked # Base dependencies uv sync --locked --extra test --extra dev # Test + dev tools uv sync --locked --extra all # Everything git lfs install
gastownhallAGENTS.mdgastownhall/beads/AGENTS.md
Issue Tracking** - How to use bd for work management - **Development Guidelines** - Code standards and testing - **Project Scope** - Read [engdocs/PROJECT_CHARTER.md](engdocs/PROJECT_CHARTER.md) before adding new feature surface area - **Visual Design System** - Status
manaflow-aiAGENTS.mdmanaflow-ai/cmux/cmux-browser/AGENTS.md
generated release composition manifest. ## Validation Run the fast host, patch-fixture, script, and protocol tests before review. Release candidates additionally require a full Chromium build, generated Chromium third-party notices
manaflow-aiAGENTS.mdmanaflow-ai/cmux/cmux-tui/AGENTS.md
bash ./scripts/verify-cmux-tui-hosted.sh --filter ./scripts/verify-cmux-tui-hosted.sh --full ``` Use `--filter` during focused development. It accepts one Rust test-name substring and verifies that the filter selects at least one test on hosted Linux
manaflow-aiAGENTS.mdmanaflow-ai/cmux/ios/AGENTS.md
wired into a Linux guard lane. Do not put new iOS-only Node tests under `scripts/lib/`: the main CI change router treats that tree as macOS-relevant, which can queue
Kilo-OrgAGENTS.mdKilo-Org/kilocode/AGENTS.md
java 21-tem`. If SDKMAN is not installed, see https://sdkman.io/install. - **Test**: `bun test` from `packages/opencode/` (NOT from root -- root blocks tests) - **Single test**: `bun test ./test/tool/tool-define.test.ts` from `packages/opencode
OpenAIAGENTS.mdopenai/symphony/elixir/AGENTS.md
recovery together before editing. - Follow `docs/logging.md` for logging conventions and required issue/session context fields. ## Tests and Validation Run targeted tests while iterating, then run full gates before handoff. - Prefer narrow
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.
