How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
agentskillsAGENTS.mdagentskills/agentskills/AGENTS.md
configuration, or policy here. ## Authority and boundaries `docs/specification.mdx` is authoritative for format requirements. Explanatory documentation, examples, tests, and implementations do not add requirements to the format. Preserve the distinction between
letta-aiAGENTS.mdletta-ai/letta/AGENTS.md
treat the high star count, package name, Docker image, release history, or old documentation as evidence that this is the current implementation. ## Use the current Letta implementation The current Letta
Model Context ProtocolAGENTS.mdmodelcontextprotocol/python-sdk/AGENTS.md
v1.x]` title prefix; only critical bug fixes and security fixes land there. - `README.md` documents v2. The v1 README lives on the `v1.x` branch. ## Package Management - ONLY use uv, NEVER
nocobaseAGENTS.mdnocobase/nocobase/AGENTS.md
components and follow its conventions. Reference https://ant.design/llms.txt for antd's LLM-friendly documentation when needed. - For frontend components and pages, follow accessibility (a11y) best practices — add appropriate ARIA
SuperClaude-OrgAGENTS.mdSuperClaude-Org/SuperClaude_Framework/AGENTS.md
house TypeScript agents with standalone `package.json`. - `skills/` holds runtime skills (e.g., `confidence-check`); `commands/` documents scripted Claude commands. - `docs/` provides reference packs; start with `docs/developer-guide` for workflow expectations. ## Build, Test
coleam00AGENTS.mdcoleam00/Archon/AGENTS.md
design in [`.archon/workflow-language-constitution.md`](.archon/workflow-language-constitution.md), aspirational engineering craft and review values in [`.archon/engineering.md`](.archon/engineering.md), user documentation in the docs site, and machine-checkable rules in code, types, tests, lint
czlonkowskiAGENTS.mdczlonkowski/n8n-mcp/AGENTS.md
Model Context Protocol server that gives AI assistants access to n8n node documentation, workflow validation, and workflow management. Documentation and validation tools work offline against the bundled SQLite node database
1Panel-devAGENTS.md1Panel-dev/MaxKB/AGENTS.md
workflow engine. A graph of `step_node/*` nodes (start, ai_chat, search_knowledge, search_document, reranker, condition, tool, mcp, loop/*, variable_*, form, document_split/extract, knowledge_write, speech/text/image/video nodes, etc.). `workflow_manage.py
NVIDIAAGENTS.mdNVIDIA/NemoClaw/AGENTS.md
maintainer, and validation plan. `Request changes`, `Defer`, and `Decline` do not authorize implementation. Small documentation corrections and low-risk fixes do not require this decision. If the product decision
NVIDIAAGENTS.mdNVIDIA/NemoClaw/docs/AGENTS.md
Documentation Agent Guide ## Role You are a documentation engineer and writer for NemoClaw public-facing documentation. Treat `docs/` as the source of truth for published content and AI-agent Markdown
NVIDIAAGENTS.mdNVIDIA/NemoClaw/fern/AGENTS.md
Fern Documentation Agent Guide You are a documentation engineer and writer responsible for the NemoClaw Fern site shell. Use this guide when editing files under `fern/`. ## Role - Maintain the Fern
NVIDIAAGENTS.mdNVIDIA/NemoClaw/src/lib/messaging/AGENTS.md
request maintainer direction, or route the integration through [Community Solutions](../../../docs/resources/community-contributions.mdx). Do not document the integration as NemoClaw behavior. Derive the channel contract from authoritative upstream documentation and source before
MicrosoftAGENTS.mdmicrosoft/onnxruntime/AGENTS.md
that is not clear from the immediate context. Do not narrate obvious code or document the sequence of approaches taken to reach the current implementation; that history belongs
GoogleAGENTS.mdgoogle/adk-python/AGENTS.md
invocation lifecycle, please refer to the `adk-architecture` skill and the referenced documentation therein. ## ADK Knowledge, Architecture, and Style Skills related to ADK development are in `.agents/skills/`. ## Project Architecture
GitHubAGENTS.mdgithub/docs/content/copilot/responsible-use/agents.md
agent can implement incremental feature requests, develop additional test suites, and create or update documentation. * **Prototyping new projects**: The cloud agent and Copilot CLI can greenfield new concepts, helping developers
JetBrainsAGENTS.mdJetBrains/intellij-community/AGENTS.md
www.asd-ste100.org/), and keep it short. This covers a comment, KDoc, a commit message, documentation, a spec, and a report to the user. Use the active voice and a simple
GoogleAGENTS.mdgoogle/filament/AGENTS.md
Filament AI Coding & Agent Guidelines This document defines machine-readable instructions and technical guardrails for AI coding assistants, agents, and LLMs working on the Filament repository. All AI-generated code
MicrosoftAGENTS.mdmicrosoft/fluentui/AGENTS.md
docs/architecture/design-tokens.md). 2. **Never use `React.FC`.** Always use `ForwardRefComponent` with `React.forwardRef`. 3. **Never access `window`, `document`, or `navigator` directly.** In v9 components, use `useFluent_unstable()` to get `targetDocument` and `targetDocument.defaultView` instead
kortix-aiAGENTS.mdkortix-ai/suna/AGENTS.md
done if the implementation is ugly - it's not done if it's not documented - it's not done if users can't discover it - it's not done
PydanticAGENTS.mdpydantic/pydantic-ai/AGENTS.md
project and its users Being an open source library, the public API, abstractions, documentation, and the code itself _are_ the product and deserve careful consideration, as much as the functionality
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.
