agentleFS
Sign inSign up

AGENTS.md examples from real projects

How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.

Best matchesWorked for most · soon
little-planetAGENTS.md

ascend-tune-lab / configuration-tuning-agents

little-planet/ascend-tune-lab/configuration-tuning-agents/AGENTS.md

vLLM-Ascend 性能优化编排 Agent。先 Read workflows/primary-workflow.md: 无 A/B/C 意图且命中白名单则走独立 skill 快路径;否则选一条平级路径。 路径 A 服务化调优:deploy-config + Phase 0→1→2(基线 / 并行策略)。 路径 B Profiling 分析:用户明确要分析且提供本地 *_ascend_pt / PROF_* 时派发。 路径 C 最佳 PD 配比:pd-deploy-config + Phase 0→1→2→3→4(检查 / AISBench / 部署 / 配比实测)。 未指定 workdir 时使用 ./workspace。不适用于训练优化、非 vLLM-Ascend 服务化部署调优。

244d agoDiscuss
RevealUIStudioAGENTS.md

revealui

RevealUIStudio/revealui/AGENTS.md

RevealUI is the agentic business runtime. People, content, offers, payments, and agents - pre-wired, open source, and ready to deploy.

53mo agoDiscuss
Agent-Rules-EcosystemAGENTS.md

infra-agent-skill

Agent-Rules-Ecosystem/infra-agent-skill/AGENTS.md

Transversal Infrastructure, CI/CD, Containerization, IaC, and Deployment Skill for AI Agents.

028d agoDiscuss
agidesignerAGENTS.md

five-step-method-skill

agidesigner/five-step-method-skill/AGENTS.md

Universal decision framework. MUST run before taking action on any request. Applies to: add feature, fix bug, implement, build, create, refactor, optimize, improve, deploy, configure, integrate, make decision, evaluate proposal, review feedback, respond to request, plan strategy, design solution, choose approach, set priority, allocate resources, launch project, hire role, define process, write proposal, draft plan, pick tool, select vendor, approve budget, schedule meeting, define scope, set deadline, write policy, change workflow, restructure team, assess risk, handle complaint, resolve conflict. ZH: 加功能, 修bug, 实现, 开发, 创建, 重构, 优化, 改进, 部署, 配置, 集成, 做决策, 评估方案, 处理反馈, 制定策略, 设计方案, 定优先级, 分配资源, 立项, 招人, 定流程, 写方案, 选工具, 排期, 开会, 定范围, 写规范, 改流程, 评估风险, 处理投诉. ES: agregar función, corregir error, implementar, construir, crear, refactorizar, optimizar, desplegar, configurar, tomar decisión, evaluar propuesta, revisar retroalimentación, planificar estrategia, contratar, definir proceso, programar reunión. JA: 機能追加, バグ修正, 実装, 構築, 作成, リファクタリング, 最適化, デプロイ, 設定, 意思決定, 提案評価, フィードバック対応, 戦略立案, 採用, プロセス定義. KO: 기능추가, 버그수정, 구현, 빌드, 생성, 리팩토링, 최적화, 배포, 설정, 의사결정, 제안평가, 피드백처리, 전략수립, 채용, 프로세스정의. FR: ajouter fonctionnalité, corriger bug, implémenter, construire, créer, refactoriser, optimiser, déployer, configurer, prendre décision, évaluer proposition, planifier stratégie. DE: Funktion hinzufügen, Bug beheben, implementieren, erstellen, refaktorisieren, optimieren, bereitstellen, konfigurieren, Entscheidung treffen, Strategie planen. The five steps: 1) Question — is this actually needed? 2) Delete — remove what shouldn't exist 3) Simplify — minimum viable approach 4) Accelerate — speed up survivors 5) Automate — only after manual validation. Prevents: over-engineering, unnecessary complexity, scope creep, premature automation.

206mo agoReads credentialsDiscuss
NousResearchAGENTS.md

hermes-agent / gateway

NousResearch/hermes-agent/gateway/AGENTS.md

every secondary-profile sender, #86905). The unscoped default-profile path (`UnscopedSecretError`) and single-profile deployments keep the `os.environ` read — there it IS the profile's own value. Never re-implement

250k6mo agoReads credentialsDiscuss
NousResearchAGENTS.md

hermes-agent / hermes_cli

NousResearch/hermes-agent/hermes_cli/AGENTS.md

only inventory — install kind, all profiles, every live gateway with supervisor + running code version. Deployment kinds are first-class: `git` updates in place; `docker`/`nix`/`apt` are NOT in-place

250k6mo agoReads credentialsDiscuss
DeepSeekAGENTS.md

deepseek-harness

deepseek-ai/deepseek-harness/AGENTS.md

shell` request/spec split is the template). - **No hardcoded tunables in plugins**: deployment-varying choices are validated `Config` fields changeable from cordis.yml; a `DEFAULT_*` constant or test hook is not configurability

238k54d agoReads credentialsDiscuss
n8n-ioAGENTS.md

n8n

n8n-io/n8n/AGENTS.md

expose the legacy or explicit-key methods. - The raw AES classes stay inside `packages/core/src/encryption/`. - **Deployment keys are never deleted** — data encrypted with a key becomes unreadable without it. Deactivate keys

206k22d agoReads credentialsDiscuss
MicrosoftAGENTS.md

vscode / common

microsoft/vscode/extensions/copilot/src/platform/authentication/common/AGENTS.md

override would disable the other required proposals. Use `resolveGitHubSessionUri` to validate and derive the deployment base; never parse an account's display label or infer its host from

193k24d agoDiscuss
Significant-GravitasAGENTS.md

AutoGPT / autogpt_platform

Significant-Gravitas/AutoGPT/autogpt_platform/AGENTS.md

hotfix/*` branch targeting `master` for incident-speed changes (model kills, routing swaps) — CD deploys on merge. See `docs/platform/contributing/managing-llm-models.md`. ### Creating Pull Requests - Create the PR against the `dev` branch

188k21d agoReads credentialsDiscuss
langgeniusAGENTS.md

dify

langgenius/dify/AGENTS.md

workflows, and RAG pipelines. This monorepo contains the backend API (`api/`), frontend application (`web/`), deployment assets (`docker/`), standalone agent backend (`dify-agent/`), CLI (`cli/`), and end-to-end suite

157k7d agoReads credentialsDiscuss
VercelAGENTS.md

next.js

vercel/next.js/AGENTS.md

create the PR. ### Adopting a Fork PR Fork PRs run without repository secrets, so deploy tests never run on them. To run those tests, a maintainer adopts

143k5mo agoReads credentialsDiscuss
VercelAGENTS.md

next.js / test

vercel/next.js/test/AGENTS.md

review instructions - During code review, flag any change that newly disables, skips, or omits deploy-mode tests or assertions, including `skipDeployment: true` and `isNextDeploy` conditionals. Only allow this when

143k5mo agoDiscuss
garrytanAGENTS.md

gstack

garrytan/gstack/AGENTS.md

most recent successful `/scrape` flow into a permanent browser-skill (fallback browser only). | ### Release + deploy | Skill | What it does | |-------|-------------| | `/ship` | Run tests, review, push, open PR. Workspace-aware version queue

134k9d agoDeletes or force-pushesDiscuss
MicrosoftAGENTS.md

generative-ai-for-beginners

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

ai.azure.com) - `AZURE_OPENAI_ENDPOINT` - Azure OpenAI endpoint URL (Foundry resource endpoint) - `AZURE_OPENAI_DEPLOYMENT` - Chat completion model deployment name (course default: `gpt-5-mini`) - `AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT` - Embeddings model

121k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

generative-ai-for-beginners / ar

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

ai.azure.com) - `AZURE_OPENAI_ENDPOINT` - عنوان نقطة نهاية Azure OpenAI (نقطة موارد Foundry) - `AZURE_OPENAI_DEPLOYMENT` - اسم نشر نموذج إكمال الدردشة (الافتراضي للدورة: `gpt-5-mini`) - `AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT` - اسم

121k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

generative-ai-for-beginners / bg

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

AZURE_OPENAI_ENDPOINT` - URL на Azure OpenAI endpoint (endpoint на Foundry ресурса) - `AZURE_OPENAI_DEPLOYMENT` - Име на deployment за чат модел (по подразбиране за курса: `gpt-5-mini`) - `AZURE_OPENAI

121k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

generative-ai-for-beginners / bn

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

ai.azure.com) - `AZURE_OPENAI_ENDPOINT` - Azure OpenAI এর এন্ডপয়েন্ট URL (Foundry রিসোর্স এন্ডপয়েন্ট) - `AZURE_OPENAI_DEPLOYMENT` - চ্যাট কমপ্লিশন মডেলের ডিপ্লয়মেন্ট নাম (কোর্সে ডিফল্ট: `gpt-5-mini`) - `AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT` - এমবেডিংস

121k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

generative-ai-for-beginners / cs

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

ai.azure.com) - `AZURE_OPENAI_ENDPOINT` - URL endpointu Azure OpenAI (endpoint Foundry resource) - `AZURE_OPENAI_DEPLOYMENT` - Název deploymentu modelu pro chat completion (výchozí pro kurz: `gpt-5-mini`) - `AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT

121k3mo agoReads credentialsDiscuss
MicrosoftAGENTS.md

generative-ai-for-beginners / da

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

ai.azure.com) - `AZURE_OPENAI_ENDPOINT` - Azure OpenAI endpoint-URL (Foundry resource endpoint) - `AZURE_OPENAI_DEPLOYMENT` - Navn på Chat completion model-udrulning (kursusstandard: `gpt-5-mini`) - `AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT` - Navn

121k3mo agoReads credentialsDiscuss
CLAUDE.md vs AGENTS.md

About AGENTS.md

What is AGENTS.md?

An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.

Where does it go?

At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.

What should it contain?

Setup and test commands, code style, and the rules a new contributor would need to know.

Does Claude Code read it?

Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.