How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
gtappsAGENTS.mdgtapps/skills/skills/probe/references/agents.md
Consult shared Claude Code probe results or test its harness behavior through a real interactive Claude session in tmux, driven by Codex, Grok CLI, or Copilot CLI. Excludes tests of those outer CLIs and application tests.
MicrosoftAGENTS.mdmicrosoft/skills/.github/plugins/deep-wiki/commands/agents.md
Generate AGENTS.md files for pertinent repository folders — only where missing. Provides coding agents with build commands, testing instructions, code style, project structure, and boundaries.
MicrosoftAGENTS.mdmicrosoft/hve-core/.github/skills/hve-core/vally-tests/references/agents.md
Nine conformance checks the vally-tests skill emits for .agent.md artifacts (including consolidated subagent structural template), with contract citations, stimulus shapes, and Vally grader recommendations
eyssetteAGENTS.mdeyssette/js-template/AGENTS.md
General Rules to Follow : coding, tests, build, lint, i18n, docs, release notes, and commit conventions.
launchapp-devAGENTS.mdlaunchapp-dev/animus-cli/.agents/skills/rust-skills/AGENTS.md
Comprehensive Rust coding guidelines with 179 rules across 14 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, API design, memory optimization, performance, testing, and common anti-patterns. Invoke with /rust-skills.
chasebuildAGENTS.mdchasebuild/fuelcheck-cli/.agents/skills/rust-skills/AGENTS.md
Comprehensive Rust coding guidelines with 179 rules across 14 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, API design, memory optimization, performance, testing, and common anti-patterns. Invoke with /rust-skills.
obraAGENTS.mdobra/superpowers/AGENTS.md
skill philosophy differs from Anthropic's published guidance on writing skills. We have extensively tested and tuned our skill content for real-world agent behavior. PRs that restructure, reword
NousResearchAGENTS.mdNousResearch/hermes-agent/agent/AGENTS.md
CHILD_ENV_MARKER` valued as the fenced Kanban board root, not a bare flag. ## Tests Loop/phase tests go in `tests/agent/`; patch the binding the phase actually reads (siblings often `from
NousResearchAGENTS.mdNousResearch/hermes-agent/AGENTS.md
provider, and turn the competing PRs into plugins against it. - **Behavior contracts over snapshots.** Tests assert how two pieces of data relate, never freeze a current value (see Testing
NousResearchAGENTS.mdNousResearch/hermes-agent/cron/AGENTS.md
root, so a child working against a scratch `HERMES_HOME` keeps a writable board. ## Tests `tests/cron/`, `tests/hermes_cli/test_kanban*.py`, `tests/tools/test_kanban*.py`. Schedule parsing and catch-up windows are pure functions — test
NousResearchAGENTS.mdNousResearch/hermes-agent/gateway/AGENTS.md
exists. A sealed native stream is a regular message — `chat.update` works (live-verified). Contract tests: `tests/gateway/test_stream_final_contract.py` (mutation-checked). Slack ground truth: `chat.*Stream` speaks STANDARD markdown, not mrkdwn; `stopStream.markdown_text
NousResearchAGENTS.mdNousResearch/hermes-agent/hermes_cli/AGENTS.md
ROOT_KEYS`). For a new key: `rg -n '" "' hermes_cli/config_defaults.py` AND `rg -n ' ' --glob '!tests' .` both hit, and one invariant test sets it in a temp `config.yaml` and asserts
NousResearchAGENTS.mdNousResearch/hermes-agent/plugins/AGENTS.md
process warning, documented replacement + migration note, ≥ 2 subsequent minor releases before removal. - Compat tests load **frozen plugins through the real discovery path** and assert outcomes — never exact registry/catalog counts, source
NousResearchAGENTS.mdNousResearch/hermes-agent/skills/AGENTS.md
every call — ship a helper script and reference it by skill-relative path. 7. **Tests at `tests/skills/test_ _skill.py`**, stdlib + pytest + `unittest.mock` only, no live network. Run `scripts/run_tests.sh tests/skills/test_ _skill.py
NousResearchAGENTS.mdNousResearch/hermes-agent/tools/AGENTS.md
spotify, terminal, todo, tts, video, vision, web, yuanbao` (don't assert the list in tests). Per-platform enable/disable via `hermes tools` (curses) or `tools. .enabled/disabled` in config.yaml. `browser_exec` replaces
NousResearchAGENTS.mdNousResearch/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.mdNousResearch/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.mdaffaan-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
affaan-mAGENTS.mdaffaan-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
DeepSeekAGENTS.mddeepseek-ai/deepseek-harness/AGENTS.md
external tools experimental/ pre-stable prototypes; public by default with explicit private exceptions test-support/ test infrastructure runtime-diagnostics/ runtime invariants util/ zero-dependency utilities python/ Python SDK/runtime (python/README.md) native
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
