AGENTS.md examples from real projects

affaan-mAGENTS.md

ECC

affaan-m/ECC/AGENTS.md

Core Principles 1. **Agent-First** — Delegate to specialized agents for domain tasks 2. **Test-Driven** — Write tests before implementation, 80%+ coverage required 3. **Security-First** — Never compromise on security; validate

No other project uses it yet

affaan-mReads credentialsAGENTS.md

ECC

affaan-m/ECC/.codex/AGENTS.md

guidance, read `docs/CODEX-NAVIGATION-GUIDE.md` after this supplement. ## Model Recommendations | Task Type | Recommended Model | |-----------|------------------| | Routine coding, tests, formatting | GPT 5.5 | | Complex features, architecture | GPT 5.5 | | Debugging, refactoring | GPT 5.5 | | Security review

TheAlgorithmsAGENTS.md

Python

TheAlgorithms/Python/AGENTS.md

change code and its doctests in the same PR.** If you're only updating tests, say so and touch nothing else. ## Code conventions (enforced by CI) - **Formatting & linting:** `ruff

No other project uses it yet

sstAGENTS.md

opencode

sst/opencode/AGENTS.md

origin/dev`, target PRs at `dev`, and diff against `origin/dev` unless told otherwise. ## Live TUI Testing - Run `bun run dev:live` from a development worktree to test its TUI against

n8n-ioReads credentialsAGENTS.md

n8n

n8n-io/n8n/AGENTS.md

Essential Commands For routine pre-commit checks, follow [Verify changes](#verify-changes). For focused tests, use `pnpm agent:test` or `pnpm agent:playwright`. Pass test files and worker limits after

No other project uses it yet

firecrawlReads credentialsAGENTS.md

firecrawl

firecrawl/firecrawl/AGENTS.md

here are the general steps you should take: 1. Write some end-to-end tests that assert your win conditions, if they don't already exist - 1 happy path (more

No other project uses it yet

MicrosoftAGENTS.md

vscode / copilotcli

microsoft/vscode/extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md

copilotCLIPrompt.ts # Prompt reference extraction and parsing │ ├── customSessionTitleService.ts │ ├── delegationSummaryService.ts │ ├── utils.ts # SessionIdForCLI namespace (URI scheme: 'copilotcli') │ └── test/ │ ├── node/ # Node.js-specific (SDK integration, filesystem, permissions) │ ├── copilotCli.ts # ICopilotCLISDK, CopilotCLIModels, CopilotCLIAgents │ ├── copilotcliSession.ts # CopilotCLISession — main session

MicrosoftAGENTS.md

vscode / agentHost

microsoft/vscode/src/vs/platform/agentHost/AGENTS.md

# Multi-Chat Architecture > Node runtime service construction is documented separately in [`node/serviceBootstrapping.md`](node/serviceBootstrapping.md). Host

No other project uses it yet

MicrosoftAGENTS.md

vscode / prompts

microsoft/vscode/src/vs/platform/agentHost/node/copilot/prompts/AGENTS.md

overridden sections) and the full config at `trace`. Keep new config shapes summarizable there. - **Tests.** `../../../test/node/agentHostPromptRegistry.test.ts` covers the registry/wiring; `../../../test/node/toolInstructions.test.ts` covers the composition/gating. Add cases there, not new harnesses

No other project uses it yet

MicrosoftAGENTS.md

vscode / node

microsoft/vscode/src/vs/platform/agentHost/test/node/AGENTS.md

Agent host unit tests For tests in this area that touch the SessionDatabase, they MUST use an in-memory database, not a real database file on disk. Use `SessionDatabase.open(':memory

instructkrReads credentialsAGENTS.md

claw-code

instructkr/claw-code/AGENTS.md

Cargo workspace: 11 crates, `claw` binary ├── src/ # Python porting workspace + reference_data/ parity snapshots ├── tests/ # Python unittest validation of src/ + scripts/ (stdlib unittest) ├── docs/ # g0XX gate verification maps + topic docs

instructkrAGENTS.md

claw-code / rust

instructkr/claw-code/rust/AGENTS.md

Anthropic Messages API. Prints `MOCK_ANTHROPIC_BASE_URL`. Dev-dep for CLI and analog tests. | | `runtime` | lib | Core: sessions, permissions, MCP, conversation loop. ~47 modules. | | `api` | lib | Provider clients: Anthropic

instructkrAGENTS.md

claw-code / src

instructkr/claw-code/src/AGENTS.md

Real logic (permissions, path scoping) | `permissions.py`, `path_scope.py` | | Query engine shim | `query_engine.py` | | Runtime simulation | `runtime.py` | | Tests | repo-root `tests/` (test_porting_workspace.py, test_security_scope.py) | Run tests: `python -m unittest discover -s tests` from repo

avelinoAGENTS.md

awesome-go

avelino/awesome-go/AGENTS.md

generator. - `.github/workflows/`: CI pipelines for PR quality validation, stale checks, site deployment, and Go tests. ## When Modifying the Awesome List - Read and respect `CONTRIBUTING.md` (alphabetical order, one item

No other project uses it yet

Significant-GravitasAGENTS.md

AutoGPT

Significant-Gravitas/AutoGPT/AGENTS.md

Styling**: Tailwind CSS only, use design tokens, Hugeicons only (through the `Icon` atom) 5. **Testing**: Integration tests (Vitest + RTL + MSW) are the default (~90%, page-level). Playwright for E2E critical

No other project uses it yet

Significant-GravitasReads credentialsAGENTS.md

AutoGPT / autogpt_platform

Significant-Gravitas/AutoGPT/autogpt_platform/AGENTS.md

files, and the `check-env-defaults-blank` pre-commit hook (plus the matching unit test in `single-container/tests/test_runtime_config.py`, which CI runs) asserts that the settings listed in `BLANK

No other project uses it yet

DietrichGebertAGENTS.md

ponytail

DietrichGebert/ponytail/AGENTS.md

task and the code it touches. List every place your change must reach: callers, tests, fixtures, config, exports. Check what your change could break for users: data it would destroy

No other project uses it yet

fReads credentialsAGENTS.md

awesome-chatgpt-prompts

f/awesome-chatgpt-prompts/AGENTS.md

AUTH_AZURE_AD_ISSUER= ``` Optional features: ``` OPENAI_API_KEY= # For AI-powered semantic search ``` ## Testing Currently no automated tests. When implementing: - Place tests adjacent to source files or in `__tests

twbsAGENTS.md

bootstrap

twbs/bootstrap/AGENTS.md

lint` / `npm run js-lint` — lint - `npm run docs-build` — build docs site - `npm test` — full test suite (lint + dist + tests + docs) ## Writing style Use ASD-STE100 Simplified Technical English

No other project uses it yet

Hugging FaceAGENTS.md

transformers

huggingface/transformers/.ai/AGENTS.md

docstrings. - `make check-repo` — `make typing` plus consistency checks. - `RUN_SLOW=1 pytest ...` — many tests are marked slow and skipped in CI. Run `make style` (or `make fix-repo

No other project uses it yet