How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Hugging FaceAGENTS.mdhuggingface/diffusers/.ai/AGENTS.md
gotchas. - **Modular pipelines** — see [modular.md](references/modular.md) for modular pipeline conventions, patterns, and gotchas. - **Tests** — see [testing.md](references/testing.md) for test conventions: required test layers, tester mixins, and dummy-component rules. - **Reporting
can1357AGENTS.mdcan1357/oh-my-pi/AGENTS.md
editing it. Check only verified checklist items; explain skipped or inapplicable checks in `Testing`. ## Code Quality - No `any` unless absolutely necessary. - **NEVER use `ReturnType<>`** — use the actual type name. - **NEVER
alibabaAGENTS.mdalibaba/nacos/AGENTS.md
agents MUST analyze the affected `test/openapi-test` coverage and update the API IT scenario matrix, test cases, and coverage registry in the same change set. If the functional path cannot
iOfficeAIAGENTS.mdiOfficeAI/AionUi/AGENTS.md
process communication must go through the IPC bridge (`packages/desktop/src/preload/`). See [docs/architecture/overview.md](docs/architecture/overview.md) for details. ## Testing **Framework**: Vitest 4 (`vitest.config.ts`). Project coverage target is ≥ 80%; ordinary changes should add focused tests
virgiliojr94AGENTS.mdvirgiliojr94/book-to-skill/AGENTS.md
SECURITY.md` and `SECURITY-NOTICE.md` — when touching parsing, files, subprocesses, generated content, or dependencies. 5. Existing tests closest to the code being changed. For the progressive-disclosure research/evaluation initiative, also read: - `docs/research/progressive-disclosure-evals.md
VercelAGENTS.mdvercel-labs/skills/AGENTS.md
modules` for skills. ## Architecture ``` src/ ├── cli.ts # Main entry point, command routing, init/check/update ├── cli.test.ts # CLI tests ├── add.ts # Core add command logic ├── add-prompt.test.ts # Add prompt behavior tests ├── add.test.ts # Add command tests ├── constants.ts
OpenAIAGENTS.mdopenai/openai-python/AGENTS.md
from the OpenAI API schema. Follow `CONTRIBUTING.md` before changing generated files. Handwritten policy, automation, tests, and examples should remain small and should not alter exported SDK APIs unless the change
tirth8205AGENTS.mdtirth8205/code-review-graph/AGENTS.md
Agent Instructions Project context (architecture, commands, conventions, tests) is in `CLAUDE.md`. This file holds the rules for every coding agent working in this repository. ## Non-Interactive Shell Commands
VercelAGENTS.mdvercel-labs/agent-skills/skills/react-view-transitions/AGENTS.md
limit. - **Naming an interactive element has a cost:** named participants are skipped by hit-testing while a transition runs ([csswg#10930](https://github.com/w3c/csswg-drafts/issues/10930)) — clicks and hover fall through
topoteretesAGENTS.mdtopoteretes/cognee/AGENTS.md
work with the cognee repository: how it’s organized, how to build, test, lint, and contribute. It mirrors our actual tooling and CI while providing quick commands for local development
googleworkspaceAGENTS.mdgoogleworkspace/cli/AGENTS.md
Manager**: Use `pnpm` instead of `npm` for Node.js package management in this repository. ## Build & Test > [!IMPORTANT] > **Test Coverage**: The `codecov/patch` check requires that new or modified lines are covered
ComposioHQAGENTS.mdComposioHQ/composio/AGENTS.md
skill references, compatibility mirrors, or validation. - `bug-fixing`: fixing a defect and choosing regression tests. - `cross-sdk-parity`: aligning TypeScript and Python behavior, generated client bumps, or API contract drift
ComposioHQAGENTS.mdComposioHQ/composio/docs/AGENTS.md
build bun run types:check bun run lint bun run lint:links bun run test bun run test:integration bun run generate:toolkits bun run generate:meta-tools
ComposioHQAGENTS.mdComposioHQ/composio/python/AGENTS.md
Python SDK guidance for AI agents. ## Scope `python/` contains the Python SDK, provider packages, tests, nox sessions, release scripts, and Python docs. ## Skill Routing - Use `python-sdk` for core
ComposioHQAGENTS.mdComposioHQ/composio/ts/AGENTS.md
agents. ## Scope `ts/` contains the TypeScript SDK packages, examples, CLI, and runtime E2E tests. ## Skill Routing - Use `typescript-sdk` for `@composio/core`, shared TypeScript package behavior, generated SDK surfaces, and modifiers
LangChainAGENTS.mdlangchain-ai/deepagents/AGENTS.md
duplicating them here: - [`libs/DEVELOPMENT.md`](libs/DEVELOPMENT.md) — repository layout, setup, commands, pre-commit, the edit-test-lint loop, testing, and benchmarks. - [`libs/ARCHITECTURE.md`](libs/ARCHITECTURE.md) — runtime structure and SDK starting points. - [`.github/RELEASING.md`](.github/RELEASING.md) — releases
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
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.
