AGENTS.md examples from real projects

yvgudeAGENTS.md

lean-ctx

yvgude/lean-ctx/AGENTS.md

cargo fast` ≈ 28 s. Leaf crates below it give no edit-time gain. - **MCP server + tools** (`rust/crates/lean-ctx-server`, lib `lean_ctx_server`): `cargo check --locked -p lean-ctx-server`. - **Agent hooks

No other project uses it yet

AvdLeeAGENTS.md

SwiftUI-Agent-Skill

AvdLee/SwiftUI-Agent-Skill/AGENTS.md

SwiftUI-specific needs only) - General Swift language features unrelated to SwiftUI - Backend or server-side Swift patterns - UIKit patterns (except when bridging is necessary) ### 2. No Code Formatting or Linting

Alpha-DojoAGENTS.md

DojoAgents

Alpha-Dojo/DojoAgents/AGENTS.md

Config/storage/data: PyYAML `>=6.0.1,<7`, pandas `>=2.2.0,<3`, pyarrow `>=14.0.0`, portalocker, APScheduler `>=3.10.0,<4` - Agent/tooling: `mcp>=1.26.0,<2`, `strands-agents`, `strands-agents-tools`, `dojosdk>=0.1.29` - Frontend: React `^19.2.6`, React

SnowLumaAGENTS.md

SnowLuma

SnowLuma/SnowLuma/AGENTS.md

client sessions into OneBot v11 actions and events, with a WebUI, TypeScript SDK, and MCP server. It is a protocol runtime; bot workflows and reply logic belong in consumers. This

AtmosphereAGENTS.md

atmosphere

Atmosphere/atmosphere/AGENTS.md

## Build System: Maven **This project uses Apache Maven with the Maven Wrapper (`./mvnw`).** ### Commands

No other project uses it yet

Model Context ProtocolAGENTS.md

java-sdk

modelcontextprotocol/java-sdk/AGENTS.md

Model Context Protocol](https://modelcontextprotocol.io), enabling Java applications to implement MCP clients and servers (sync and async) over stdio, SSE, and Streamable HTTP transports. ## Modules - `mcp-core` — protocol types, schema

No other project uses it yet

IgnisDaAGENTS.md

ryot

IgnisDa/ryot/AGENTS.md

code quality and consistency. ## Project Architecture & Tools ### Code Navigation Use tools from the Serena MCP (if available) for faster code navigation and retrieval. It supports Rust and TypeScript. ### Monorepo Management

kialiAGENTS.md

kiali

kiali/kiali/AGENTS.md

mcp.json`** The project includes a `.mcp.json` at the repo root with a `cypress-debugger` MCP server that connects to the Cypress Chrome browser on port 9222: ```json { "mcpServers": { "cypress-debugger

crmneAGENTS.md

zapfast

crmne/zapfast/AGENTS.md

reading and writing their own chats by hand. It will not have bots, an MCP server, or any API, command-line, plugin or scripting interface that reads, exports or sends

smallcloudaiAGENTS.md

refact

smallcloudai/refact/AGENTS.md

/gui/**` | `npm test` → `format:check` → `types` → `lint` → `build` (Node LTS + latest) | | `server_build` | `refact-server/**` | Docker multi-arch build | | `docs_build` | `docs/**` | Docker build + push | | `plugin_vscode_build` | `plugins/vscode/**`, engine

scenario-labsAGENTS.md

skills

scenario-labs/skills/AGENTS.md

knowledge that teaches AI coding agents to create production-ready content through the [Scenario MCP server](https://mcp.scenario.com). The content spans images, video, audio, textures, skyboxes, 3D, and custom models

No other project uses it yet

AWSAGENTS.md

agentcore-samples / codex

awslabs/agentcore-samples/01-features/02-host-your-agent/01-runtime/04-coding-agents/03-code-agents-competition-e2e/coding_agents/codex/AGENTS.md

reading issues, applying fixes, and submitting PRs. ## MCP Tools You have a `gateway` MCP server connected that provides GitHub tools. Use them directly — they are available as native tools. ## Behavior

AWSAGENTS.md

agentcore-samples / open-code

awslabs/agentcore-samples/01-features/02-host-your-agent/01-runtime/04-coding-agents/03-code-agents-competition-e2e/coding_agents/open-code/AGENTS.md

reading issues, applying fixes, and submitting PRs. ## MCP Tools You have a `gateway` MCP server connected that provides GitHub tools. Use them directly — they are available as native tools. ## Behavior

JohannesKlaussAGENTS.md

react-hotkeys-hook

JohannesKlauss/react-hotkeys-hook/AGENTS.md

Development Workflow - Use `packages/lab` to reproduce bugs - Verify behavior with the playwright mcp ## Development Commands ### Build and Development - `npm run build` - Build the main library package (runs in packages/react-hotkeys-hook

AtomicBot-aiAGENTS.md

atomic-agent

AtomicBot-ai/atomic-agent/AGENTS.md

instructions](src/tui/AGENTS.md); [module guide](src/tui/README.md). - `channels/`: [channels instructions](src/channels/AGENTS.md); [module guide](src/channels/README.md). - `mcp/`: [mcp instructions](src/mcp/AGENTS.md); [module guide](src/mcp/README.md). - `skills/`: [skills instructions](src/skills/AGENTS.md); [module guide](src/skills/README.md). - `tasks/`: [tasks instructions](src/tasks/AGENTS.md

No other project uses it yet

superlinkedAGENTS.md

sie

superlinked/sie/AGENTS.md

repository is the source of truth for the open-source SIE server, SDKs, gateway, sidecar, configuration service, MCP service, Helm chart, and public release automation. Keep changes self-contained

ColeMurrayAGENTS.md

background-agents

ColeMurray/background-agents/AGENTS.md

Dependency Graph ``` @open-inspect/shared ← control-plane, web, slack-bot, github-bot, linear-bot, mcp-server @open-inspect/control-plane ← preview ``` **Build `@open-inspect/shared` first** whenever you change shared types

revolistAGENTS.md

revogrid

revolist/revogrid/AGENTS.md

first when available Use the hosted RevoGrid MCP endpoint: ```text https://mcp.rv-grid.com ``` If the MCP server is available in the client: 1. search RevoGrid MCP before writing code 2. prefer

hi-godotAGENTS.md

godot-ai

hi-godot/godot-ai/AGENTS.md

subscription and deliver events to the task. ## What this project is A production-grade MCP server for Godot. Python server (FastMCP v3) communicates over WebSocket with a GDScript editor plugin

No other project uses it yet

himself65AGENTS.md

finance-skills

himself65/finance-skills/AGENTS.md

data-providers/ # External API data (Adanos, Fintel, Hormuz Strait, TradingView, Hyperliquid) plugin.json .mcp.json # Bundled MCP servers (tradingview — headless TradingView scanner, pinned to a git SHA) skills/... startup-tools/ # Startup analysis

No other project uses it yet