AGENTS.md examples from real projects

bytedanceAGENTS.md

deer-flow / video-generation

bytedance/deer-flow/skills/public/video-generation/AGENTS.md

invalid duration string is reported before submission. The provider checks the model-specific combinations. - **Tests mock HTTP and check request metadata and the exact input bytes** for both providers. Offline

heygen-comAGENTS.md

hyperframes

heygen-com/hyperframes/AGENTS.md

changes only within the task's authorization and verify the resulting GitHub state. ## Build & Test ```bash bun install # Install dependencies (NOT pnpm — do not create pnpm-lock.yaml) bun run build # Build

heygen-comAGENTS.md

hyperframes

heygen-com/hyperframes/docs/AGENTS.md

page, read its complete body and verify product behavior in the current source, tests, CLI help, or shipped skills. - Write for a smart general user first. Do not assume they

No other project uses it yet

jesseduffieldAGENTS.md

lazygit

jesseduffield/lazygit/AGENTS.md

Windows box has only `just`). - `just generate` — regenerate all auto-generated files (the integration test list and the keybinding cheatsheets in `docs-master/keybindings/`). Run this whenever you add/remove/rename

No other project uses it yet

opendatalabAGENTS.md

MinerU

opendatalab/MinerU/AGENTS.md

bash # 在项目根目录中创建虚拟环境 uv venv .venv # 激活虚拟环境 source .venv/bin/activate # 安装依赖 uv pip install -e ".[dev,test]" ``` 运行 Python 代码须在项目根目录 `MinerU` 中执行： ```bash .venv/bin/python -m mineru.path.to.submodule ``` ## GitHub Issue / PR 处理规范 处理 GitHub

santiferReads credentialsAGENTS.md

career-ops

santifer/career-ops/AGENTS.md

filter`; optional `domain_filter` gates whole boards on industry relevance before any title is tested (opt-in, #3105); checkpoints every 500 companies, `--resume` continues an interrupted sweep | | `scan-interamt.mjs` | Playwright browser

santiferAGENTS.md

career-ops / web

santifer/career-ops/web/AGENTS.md

matches tailored CVs and canonicalises statuses: call it, or mirror it behind a parity test. A second implementation of the same rule is how the two halves start disagreeing

netdataReads credentialsAGENTS.md

netdata

netdata/netdata/AGENTS.md

decisions, design forks, risk acceptance, destructive approvals, final product judgment. - **Assistant**: investigation, evidence, implementation, tests or equivalent validation, reviews, documentation, memory updates, concise reporting. The assistant proposes and investigates

No other project uses it yet

calesthioAGENTS.md

OpenMontage / flux-best-practices

calesthio/OpenMontage/.agents/skills/flux-best-practices/AGENTS.md

costs at different resolutions. **Creative Exploration / Ideation:** **Recommended: FLUX.2 [klein]** - Fast iterations - Quick concept testing - Mood board generation - Exploring prompt variations **Production Marketing Assets:** **Recommended: FLUX.2 [pro]** - Consistent quality - Reasonable

ruvnetReads credentialsAGENTS.md

claude-flow

ruvnet/claude-flow/AGENTS.md

point. Codex agents are the executors. Coordination records do not write code or run tests. Use `guidance_brain({ mode: "recommend", task: "..." })` to select Ruflo capabilities from the live MCP registry

abiReads credentialsAGENTS.md

screenshot-to-code

abi/screenshot-to-code/AGENTS.md

environment: - `cd backend && poetry env activate` (then run the `source .../bin/activate` command it prints) Testing policy: - Always run backend tests after every code change: `cd backend && poetry run pytest`. - Always

No other project uses it yet

headroomlabs-aiAGENTS.md

headroom

headroomlabs-ai/headroom/AGENTS.md

needs a "Real behavior proof" section (setup, exact commands, observed output, what was not tested). Bug fixes need a test that fails before the fix. - One docs site: `docs/`, deployed

storytoldAGENTS.md

photocraft

storytold/photocraft/AGENTS.md

code, even when someone names a location. 4. **Keep fixes narrow and tested.** Fix what the issue describes, where the bug is. Add a test that fails without

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners

microsoft/ai-agents-for-beginners/AGENTS.md

agents visible in Foundry portal) - Production-ready with built-in observability - File pattern: `*-python-agent-framework.ipynb` ## Testing Instructions This is an educational repository with example code rather than production code with automated

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners / ar

microsoft/ai-agents-for-beginners/translations/ar/AGENTS.md

azure-identity)" ``` 2. **اختبر تنفيذ دفتر جوبيتر:** ```bash # Convert notebook to script and run (tests imports) jupyter nbconvert --to script /code_samples/ .ipynb --stdout | python ``` 3. **تحقق من متغيرات البيئة:** ```bash

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners / bg

microsoft/ai-agents-for-beginners/translations/bg/AGENTS.md

azure-identity)" ``` 2. **Тествайте изпълнението на ноутбук:** ```bash # Convert notebook to script and run (tests imports) jupyter nbconvert --to script /code_samples/ .ipynb --stdout | python ``` 3. **Проверете променливите на средата:** ```bash

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners / bn

microsoft/ai-agents-for-beginners/translations/bn/AGENTS.md

azure-identity)" ``` ২. **নোটবুক কার্যকরীতা টেস্ট করুন:** ```bash # Convert notebook to script and run (tests imports) jupyter nbconvert --to script /code_samples/ .ipynb --stdout | python ``` ৩. **পরিবেশ পরিবর্তনশীল যাচাই করুন:** ```bash

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners / cs

microsoft/ai-agents-for-beginners/translations/cs/AGENTS.md

azure-identity)" ``` 2. **Otestujte spuštění notebooku:** ```bash # Convert notebook to script and run (tests imports) jupyter nbconvert --to script /code_samples/ .ipynb --stdout | python ``` 3. **Ověřte proměnné prostředí:** ```bash python

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners / da

microsoft/ai-agents-for-beginners/translations/da/AGENTS.md

Testvejledning Dette er et uddannelsesrepository med eksempel kode i stedet for produktionskode med automatiske tests. For at verificere din opsætning og ændringer: ### Manuel test 1. **Test Python miljø:** ```bash python

No other project uses it yet

MicrosoftReads credentialsAGENTS.md

ai-agents-for-beginners / de

microsoft/ai-agents-for-beginners/translations/de/AGENTS.md

Dateimuster: `*-python-agent-framework.ipynb` ## Testanweisungen Dies ist ein Lern-Repository mit Beispielcode, kein Produktionscode mit automatisierten Tests. Zur Überprüfung Ihrer Einrichtung und Änderungen: ### Manuelles Testen 1. **Python-Umgebung testen:** ```bash python --version

No other project uses it yet