AGENTS.md examples from real projects

OpenAIAGENTS.md

openai-node

openai/openai-node/AGENTS.md

meaningful public JSDoc. Preserve documentation URLs/import paths; examples must run with documented environments/dependencies. ## Security and lifecycle correctness Read and apply [contributor security requirements](.github/CONTRIBUTING.md#security-requirements) for credentials/synthetic fixtures, browser

No other project uses it yet

TEN-frameworkAGENTS.md

ten-framework

TEN-framework/ten-framework/AGENTS.md

them upfront. This gives you setup, architecture, code map, conventions, workflows, interfaces, gotchas, and security. 3. If a task needs more detail than L1 provides, follow links to L2 deep

LangChainAGENTS.md

open-swe

langchain-ai/open-swe/AGENTS.md

tests that do. - No speculative edge cases or the same behavior tested across layers. Security, authorization, data integrity, and tricky state transitions do deserve targeted coverage. - For bug fixes, prefer

bunkerityAGENTS.md

bunkerweb

bunkerity/bunkerweb/AGENTS.md

changes with maintainers and flag them clearly in both commit body and PR description. ## Security & Configuration Tips Never commit secrets—use sample files in `env/` or add new templates when

No other project uses it yet

tambo-aiAGENTS.md

tambo

tambo-ai/tambo/.github/AGENTS.md

GitHub Actions workflows: - **Pin actions to full commit SHA** with a version comment for security and reproducibility: ```yaml # Good - pinned to SHA with version comment - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2

nexmoeAGENTS.md

VidBee

nexmoe/VidBee/AGENTS.md

Prefer simple conditionals over nested ternary operators - Group related code together and separate concerns ### Security - Add `rel="noopener"` when using `target="_blank"` on links - Avoid `dangerouslySetInnerHTML` unless absolutely necessary

chimuraiAGENTS.md

http-proxy-middleware

chimurai/http-proxy-middleware/AGENTS.md

markdown code block. NEVER include secrets, PII, or proprietary prompt content ## GitHub PR and Security Advisories - If the user asks you to open a GitHub PR or create a GitHub

apacheAGENTS.md

thrift

apache/thrift/AGENTS.md

code** (i.e., in the same directory) takes precedence on any conflict. --- ## 6. Security Work When assisting with security-sensitive changes (transport size limits, TLS configuration, authentication, serialization bounds, or anything

mauticAGENTS.md

mautic

mautic/mautic/AGENTS.md

Unit + Functional tests │ ├── Unit/ │ └── Functional/ └── Views/ # Twig templates ``` ### Key Core Bundles - **CoreBundle**: Foundation (helpers, security, base classes) - **LeadBundle**: Contact/company management - **CampaignBundle**: Campaign builder & execution - **EmailBundle**: Email marketing - **FormBundle**: Form builder

dotnetAGENTS.md

orleans

dotnet/orleans/AGENTS.md

Implementation principles Apply these principles during design, implementation, and validation, alongside correctness, security, compatibility, concurrency, and reliability. ## Priorities - Rank goals as correctness (including safety) > simplicity > performance > convenience; seek a design

No other project uses it yet

dotnetAGENTS.md

orleans

dotnet/orleans/docs/AGENTS.md

Configure it with <xref:Orleans.Hosting.AzureTableSiloBuilderExtensions.AddAzureTableGrainStorage*?displayProperty=nameWithType>. ``` ## Documentation types Address relevant operational concerns: correctness, security, availability, upgrades, capacity, cost, and diagnosis under load. - **Architecture**: components, protocols, invariants, consistency, failure

No other project uses it yet

47ngAGENTS.md

nuqs

47ng/nuqs/AGENTS.md

Workflow](.agents/docs/git-workflow.md)** — Conventional commits, semantic versioning, PR standards - **[Quality Standards](.agents/docs/quality-standards.md)** — Checklists, performance, security, anti-patterns --- ## Quick Reference: Common Tasks | Task | Guide | | ----------------------- | --------------------------------------------------------------------------------- | | Fix a bug | See [Testing Patterns](.agents/docs/testing.md) → Regression

No other project uses it yet

go-vgoAGENTS.md

robotgo

go-vgo/robotgo/AGENTS.md

pure-Go `darwin/` backends). When reproducing bugs on darwin, verify System Settings → Privacy & Security first. - **Do not vendor**: `vendor/` is in `.gitignore`; also avoid `go mod vendor` (upstream note

No other project uses it yet

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

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

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

No other project uses it yet

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

benoitcAGENTS.md

gunicorn

benoitc/gunicorn/AGENTS.md

doubt whether a change is protocol code, it is. ## Specification issues are bugs, not security issues A report is a specification issue when the fix is to make gunicorn

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

No other project uses it yet

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