AGENTS.md examples from real projects

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

Best matches · from page 15Worked for most · soon

dagucloudAGENTS.md

dagu / ui

dagucloud/dagu/ui/AGENTS.md

DAGs by name, tags, or content - **Remote Node Support**: Manage workflows across multiple environments ### 🔒 **Security & Configuration** - **Authentication**: - Basic authentication (username/password) - API token authentication - TLS/HTTPS support with cert/key files - **Permissions**: - `writeDAGs

4.2k5mo agoDiscuss

kirodotdevAGENTS.md

KiroCrew

kirodotdev/KiroCrew/AGENTS.md

seam, governance | [platform-context](docs/system-specs/modules/platform-context.md) + [governance](docs/system-specs/modules/governance.md) | | `security.py`, `hooks.py`, denied commands, sensitive paths | [security](docs/system-specs/modules/security.md) + [sel](docs/system-specs/modules/sel.md) | | `config/` — the live watcher, `restart=True` marks, appliers, `config.json` writes | [config](docs/system-specs/modules/config.md

4.2k32d agoReads credentialsDiscuss

kirodotdevAGENTS.md

KiroCrew / website

kirodotdev/KiroCrew/website/AGENTS.md

focus stop rather than a nested button. Enforced by `AUTOSDE.yaml` (`errors-use-error-notice`). - **Security: every `dangerouslySetInnerHTML` goes through DOMPurify** via `md()` / `sanitize()` / `esc()` in `src/api/helpers.ts`. A bypass

4.2k32d agoDiscuss

melgarafaelAGENTS.md

DeskcommCRM

melgarafael/DeskcommCRM/AGENTS.md

helper (`fn_user_org_ids()`/`fn_user_role_in_org()`), a mesma função SECURITY DEFINER que o RBAC de aplicação usa. Schema versionado em `supabase/migrations/`; o que o self-host

4.2k13d agoReads credentialsDiscuss

flypythoncomAGENTS.md

python

flypythoncom/python/AGENTS.md

safety requirements. - Do not call a project production-ready without current maintenance, licensing, security, and adoption evidence. - Do not use an LLM or web-search API to generate resource descriptions

4.1k20d agoDiscuss

abhi1693AGENTS.md

openclaw-mission-control

abhi1693/openclaw-mission-control/AGENTS.md

check` or targeted commands), linked issue, and screenshots/logs when UI or operator workflow changes. ## Security & Configuration Tips - Never commit secrets. Copy from `.env.example` and keep real values in local

4.1k7mo agoReads credentialsDiscuss

nyldnAGENTS.md

claude-octopus

nyldn/claude-octopus/AGENTS.md

4.1k49d agoReads credentialsDiscuss

nyldnAGENTS.md

claude-octopus

nyldn/claude-octopus/docs/AGENTS.md

This Tentacle | Why This One? | |---------------------|-------------------------|---------------| | Design a REST/GraphQL API | `backend-architect` | Microservices maestro | | Find security vulnerabilities | `security-auditor` | OWASP whisperer | | Debug failing tests | `debugger` | Stack trace detective | | Implement with

4.1k49d agoDiscuss

davidondrejAGENTS.md

skills

davidondrej/skills/AGENTS.md

overthinking!) - if you are in a worktree, configure required environment variables securely ## SECRETS - Never commit `.env` files, API keys, tokens, cookies, etc. - Keep browser/client code limited to public or anon

4.1k4d agoReads credentialsDiscuss

liustackAGENTS.md

modlens

liustack/modlens/AGENTS.md

fixes), `harness-setup` (how a pasted image reaches the model in each harness), `security` (recovered-image privacy, permissions passed to engines, untrusted image content), `testing`, `commit`, `research-gemini-claude-skills

4.1k50d agoReads credentialsDiscuss

basicmachines-coAGENTS.md

basic-memory

basicmachines-co/basic-memory/AGENTS.md

cloud synchronization and storage (requires active subscription): **Authentication:** - JWT-based authentication with subscription validation - Secure session management with token refresh - Support for multiple cloud projects **Bidirectional Sync:** - rclone bisync integration

4.1k2mo agoReads credentialsDiscuss

Gaurav-GosainAGENTS.md

tuios

Gaurav-Gosain/tuios/AGENTS.md

Note:** The web terminal functionality is provided by the separate `tuios-web` binary for security isolation. See `cmd/tuios-web/` and [docs/WEB.md](docs/WEB.md) for details. ## Essential Commands ### Build & Run ```bash # Build from

4k8d agoDiscuss

CloudflareAGENTS.md

kumo

cloudflare/kumo/AGENTS.md

local `vite-plus` dependency (`pnpm vp …`), and hooks resolve it from `node_modules/.bin`. ## SECURITY - **NEVER commit** Figma tokens, npm tokens, or API keys - `.env` files are gitignored - `wrangler.jsonc` contains Cloudflare

3.9k2mo agoReads credentialsDiscuss

CloudflareAGENTS.md

kumo / ci

cloudflare/kumo/ci/AGENTS.md

Visual regression**: Creates ephemeral `vr-screenshots-{pr}-{runId}` branches for diff images - **Fork PR security**: `docs-preview-post-build.yml` handles fork PRs via `workflow_run` (no secrets in fork context) - **Composite action**: `.github/actions/install-dependencies/action.yml

3.9k2mo agoReads credentialsDiscuss

CloudflareAGENTS.md

kumo / kumo-screenshot-worker

cloudflare/kumo/packages/kumo-screenshot-worker/AGENTS.md

These are set via `vrSection` and `vrTitle` props on `ComponentExample.astro` in the docs site. ## SECURITY NOTES - **URL validation**: all Browser Rendering targets must be `https://` and match the explicit Kumo

3.9k2mo agoReads credentialsDiscuss

MicrosoftAGENTS.md

apm / hello-world

microsoft/apm/templates/hello-world/AGENTS.md

best practices. You prioritize: - Clear, readable code with good documentation - Test-driven development approaches - Security-first design patterns - Performance optimization where appropriate When working on any task, always consider

3.9k14d agoDiscuss

MicrosoftAGENTS.md

PhiCookBook

microsoft/PhiCookBook/AGENTS.md

model usage should follow Microsoft's Responsible AI principles: - Fairness, reliability, safety - Privacy and security - Inclusiveness, transparency, accountability - Use Azure AI Content Safety for production applications - See `/md/01.Introduction/01/01.AISafety.md` ### Translations

3.9k7mo agoDiscuss

MicrosoftAGENTS.md

PhiCookBook / en

microsoft/PhiCookBook/translations/en/AGENTS.md

3.9k7mo agoDiscuss

MicrosoftAGENTS.md

PhiCookBook / pcm

microsoft/PhiCookBook/translations/pcm/AGENTS.md

model usage suppose follow Microsoft's Responsible AI principles: - Fairness, reliability, safety - Privacy and security - Inclusiveness, transparency, accountability - Use Azure AI Content Safety for production applications - See `/md/01.Introduction/01/01.AISafety.md` ### Translations

3.9k7mo agoDiscuss

MicrosoftAGENTS.md

PhiCookBook / zh-CN

microsoft/PhiCookBook/translations/zh-CN/AGENTS.md

3.9k7mo agoDiscuss

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.