agentleFS

AGENTS.md examples from real projects

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

Best matches · from page 23Worked for most · soon
WasmEdgeAGENTS.md

WasmEdge

WasmEdge/WasmEdge/AGENTS.md

workflows | | lineguard | `misc-linters.yml` | Trailing whitespace, final newline | | codespell | `misc-linters.yml` | Catches common typos | | CodeQL | `codeql-analysis.yml` | Security analysis | | IWYU | `IWYU_scan.yml` | Include-what-you-use | | Infer | `static-code-analysis.yml` | Static code analysis | | Symbol exposure | `reusable

11k4mo agoReviewMountCreate a free account to mount
Chia-NetworkAGENTS.md

chia-blockchain

Chia-Network/chia-blockchain/AGENTS.md

before block inclusion. Fee priority is cost-based. - **35 condition opcodes.** Canonical source: `chia/types/condition_opcodes.py`. ## Security / Anti-Goals - **Never push transactions** (`push_tx`) without explicit user confirmation. - **Never construct spend bundles

11k5d agoReviewMountCreate a free account to mount
FreikaReads credentialsAGENTS.md

dawarich

Freika/dawarich/AGENTS.md

Discussions for larger changes and request review from domain owners (imports, sharing, trips, etc.). ## Security & Configuration Tips Start from `.env.example` or `.env.template` and store secrets in encrypted Rails credentials; never

11k14mo agoReviewMountCreate a free account to mount
ChatGPTBox-devDeletes or force-pushesAGENTS.md

chatGPTBox

ChatGPTBox-dev/chatGPTBox/AGENTS.md

with platform-specific build settings ### Cross-Browser Compatibility - Uses `webextension-polyfill` for API compatibility ## Security & Privacy - Do not commit secrets, API keys, or user data - Keep manifest permissions minimal

11k4y agoReviewMountCreate a free account to mount
nextcloudAGENTS.md

all-in-one

nextcloud/all-in-one/AGENTS.md

github.com/nextcloud/.github/blob/master/AI_POLICY.md)** - the primary reference for AI-specific rules, covering disclosure, author accountability, communication, security, licensing, code quality, and autonomous agent behavior. - **[Contribution Guidelines](https://github.com/nextcloud/all-in-one/blob/main/CONTRIBUTING.md)** - covering testing requirements

No other project uses it yet

11k10mo agoReviewMountCreate a free account to mount
we-promiseReads credentialsAGENTS.md

sure

we-promise/sure/AGENTS.md

relevant failures and partial responses, with provider/source metadata and family/account-provider context where available. - For securities providers, follow [adding a securities provider](docs/llm-guides/adding-a-securities-provider.md). - For feature rollout, follow [preview-feature gating](docs/llm-guides/gating-a-preview-feature.md

No other project uses it yet

11k57d agoReviewMountCreate a free account to mount
MetaAGENTS.md

hydra

facebookresearch/hydra/AGENTS.md

repo's lint sessions include formatting, import sorting, type checks, style, YAML linting, and security checks. For focused local checks, use the same tools the noxfile runs: - `ruff format .` / `ruff

11k5d agoReviewMountCreate a free account to mount
yugabyteAGENTS.md

yugabyte-db / src

yugabyte/yugabyte-db/src/AGENTS.md

dummy_token`. - **YugabyteDB-internal information not yet public** — unreleased roadmap details, internal SLAs, embargoed security findings, internal infra hostnames. Common leak paths that slip past a scrub of the prose

11k4mo agoReviewMountCreate a free account to mount
baptisteArnoReads credentialsAGENTS.md

typebot.io

baptisteArno/typebot.io/AGENTS.md

minimal Playwright shape such as `{ name, value, url: "http://localhost:3000", expires, httpOnly, secure, sameSite }`. - Prefer `http://localhost:3000` over `127.0.0.1:3000` when reusing that auth file, since the saved

11k4mo agoReviewMountCreate a free account to mount
woocommerceAGENTS.md

woocommerce

woocommerce/woocommerce/AGENTS.md

independent human review is always required (anything on the High-Impact list, plus security, privacy, data integrity, backward compatibility, and performance-sensitive paths). Two rules matter for agents: - Never present

11k2mo agoReviewMountCreate a free account to mount
GoogleReads credentialsAGENTS.md

adk-recipes / genmedia-for-commerce

google/adk-recipes/core/python/genmedia-for-commerce/AGENTS.md

generic one for anything else (log the details). - Browser side: an enforced CSP and security headers outside `/mcp` (`api/security_headers.py`); CORS same-origin unless `ALLOW_ORIGINS` lists origins (`*` is refused

11k35d agoReviewMountCreate a free account to mount
GoogleReads credentialsAGENTS.md

adk-recipes / long-horizon-harness

google/adk-recipes/core/python/long-horizon-harness/AGENTS.md

prefix, prefix cache, the four bounds on context growth), and [`docs/security-model.md`](docs/security-model.md) (per-layer security). Don't duplicate those here — link to them. ## What this recipe teaches Horizon leans

11k35d agoReviewMountCreate a free account to mount
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.