AGENTS.md examples from real projects

NousResearchAGENTS.md

hermes-agent / tests

NousResearch/hermes-agent/tests/AGENTS.md

tests/ — how Hermes tests are written and run Applies on top of the root `AGENTS.md`. Read it before adding or changing any test. ## Running tests **ALWAYS use `scripts/run_tests.sh`**, never bare

NousResearchReads credentialsAGENTS.md

hermes-agent / tools

NousResearch/hermes-agent/tools/AGENTS.md

search, skills, terminal, todo, tts, video, vision, web` (don't assert the list in tests). Per-platform enable/disable via `hermes tools` (curses) or `tools. .enabled/disabled` in config.yaml. `browser_exec

NousResearchReads credentialsAGENTS.md

hermes-agent / tui_gateway

NousResearch/hermes-agent/tui_gateway/AGENTS.md

import; the dispatcher rejects unknown param keys (`4000` + key path) and, under `HERMES_TEST_ISOLATION=1`, raises `ContractViolation` when a handler's result or an emitted payload does not match

NousResearchAGENTS.md

hermes-agent / web

NousResearch/hermes-agent/web/AGENTS.md

surface; a new surface is a new `web_routers/ .py`, not a growing `web_server.py`. - Tests: Python in `tests/hermes_cli/` (routers, pty bridge); JS in the `web/` vitest suite. Python tests must

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

anomalycoAGENTS.md

opencode

anomalyco/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

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

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

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

microsoft/vscode/.eslint-plugin-local/AGENTS.md

commit hook, `pnpm run oxlint`, the oxc editor extension and the rule tests, through oxlint's `RuleTester`), which loads them as JS plugins. They use oxlint's ESLint-compatible rule

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

No other project uses it yet

MicrosoftAGENTS.md

vscode / agentHost

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

# Multi-Chat Architecture > Before adding or changing protocol constructs or `_meta`, follow [AHP interoperability

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

No other project uses it yet

instructkrReads credentialsAGENTS.md

clawd-code

instructkr/clawd-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

clawd-code / rust

instructkr/clawd-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

clawd-code / src

instructkr/clawd-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

polish on the live app. 4. `Tech Debt & Improvements (QN YYYY)` for refactors, cleanup, tests, dev experience and infra. 5. `Feature Suggestions (QN YYYY)` for ideas and requests nobody