AGENTS.md examples from real projects

CloudflareReads credentialsAGENTS.md

agents / examples

cloudflare/agents/examples/AGENTS.md

simple, clear, and consistent. Each example should focus on **one feature or concept** (e.g., MCP servers, email routing, workflows). The exception is `playground/`, which is the kitchen-sink showcase covering

No other project uses it yet

CloudflareReads credentialsAGENTS.md

agents / agents

cloudflare/agents/packages/agents/AGENTS.md

wrapper for SDK v2 stateless servers | | `agents/mcp/client` | `src/mcp/client/index.ts` | MCP client manager (connect to remote MCP servers from an Agent) | | `agents/email` | `src/email.ts` | Email routing, resolvers, header signing | | `agents/workflows` | `src/workflows.ts` | `AgentWorkflow` — Workflows

No other project uses it yet

agentscope-aiAGENTS.md

HiClaw

agentscope-ai/HiClaw/AGENTS.md

tests/) — integration test suite ### To modify Higress routing and initialization - [manager/scripts/init/setup-higress.sh](manager/scripts/init/setup-higress.sh) — route, consumer, MCP server setup (local / full console mode) - [design/higress-console-api.yaml](design/higress-console-api.yaml) — Higress Console API spec (OpenAPI 3.0) ## Technology

VercelAGENTS.md

eve

vercel/eve/AGENTS.md

answer back. 5. **Discoverability determines whether agents find you at all.** `llms.txt`, typed SDKs, MCP servers, machine-readable specs. If an agent can't discover your surface, it reaches

VercelReads credentialsAGENTS.md

eve / eve-software-factory-template

vercel/eve/apps/templates/eve-software-factory-template/AGENTS.md

brain`, gated by `factoryBrainPolicy` so unattended runs can't write shared context). - **Connections** are MCP servers: `linear` (`https://mcp.linear.app/mcp`, app-scoped auth shared through `linearAuth` in `agent/lib/constants.ts`). Its connection

VercelReads credentialsAGENTS.md

eve / kody-eve-template

vercel/eve/apps/templates/kody-eve-template/AGENTS.md

ctx.agent()` and requests structured output per turn (`defineAgent` no longer takes `outputSchema`). - **Connections** are MCP servers: `linear` (`https://mcp.linear.app/mcp`, app-scoped auth shared through `linearAuth` in `agent/lib/constants.ts` with scopes

VercelReads credentialsAGENTS.md

eve / marketing-team-eve-template

vercel/eve/apps/templates/marketing-team-eve-template/AGENTS.md

Mail cannot be recalled, so the Resend surface is an allow list.** Resend's MCP server publishes around 85 tools spanning campaigns, contacts, domains, webhooks, and API keys, of which

awarexoneAGENTS.md

Agentic-Bug-Hunter

awarexone/Agentic-Bug-Hunter/AGENTS.md

poisoning | | `skills/graphql-audit/` | GraphQL hunting — introspection, field suggestions, batching DoS, IDOR via aliasing, injection | | `skills/mcp-server-audit/` | MCP server audit — tool poisoning, param→sink injection, missing approval gates, secret leaks, rug-pull/confused-deputy

talebookAGENTS.md

talebook

talebook/talebook/AGENTS.md

app/test/` 中添加用例。 - 具体写法见各子目录的 CLAUDE.md。 ### 前端验收 - 修改前端交互、样式、主题、页面布局或弹窗时，除单元/组件测试外，必须使用 Chrome DevTools MCP 在浏览器中做实际渲染验证，并在回复中说明验证过的页面、主题或关键状态。 - 修改界面时允许使用 mock API 完成组件测试、E2E 和快速回归等隔离自测。mock 环境只服务于自动化测试或智能体内部验证，不得作为用户体验环境、实际数据验收或完整功能验证结果。 - 用户要求本地体验、查看实际效果或提供可访问地址时

tuistAGENTS.md

tuist / atlas

tuist/tuist/atlas/AGENTS.md

OAuth or shared bearer-token upstreams at `/admin/mcps` through the server modals. The `create_mcp_server` and `delete_mcp_server` tools provide add and remove operations. These rows are read

No other project uses it yet

tuistAGENTS.md

tuist / condukt

tuist/tuist/condukt/AGENTS.md

Condukt The independently published `condukt` Hex package lives here. Server and Atlas use `path: "../condukt"`; keep the library's own dependencies registry-based so external consumers do not need

No other project uses it yet

tuistAGENTS.md

tuist / infra

tuist/tuist/infra/AGENTS.md

# Infrastructure Deployment assets for the Tuist stack — both the managed cluster we operate and

No other project uses it yet

tuistAGENTS.md

tuist / pulse

tuist/tuist/pulse/AGENTS.md

# Pulse A headless, open-source observability backend: unified logs/metrics/traces access, built-in alerting, and

No other project uses it yet

freelensappReads credentialsAGENTS.md

freelens

freelensapp/freelens/AGENTS.md

working on a task — scratch scripts, command output, screenshots, DOM/accessibility snapshots, and AI-agent / MCP-server runtime artifacts — must never be written into the tracked working tree, or they leak

No other project uses it yet

jgraphAGENTS.md

drawio-mcp

jgraph/drawio-mcp/AGENTS.md

Draw.io MCP Server The official draw.io MCP (Model Context Protocol) server that enables LLMs to open and create diagrams in the draw.io editor. ## Repository Structure - **`.claude-plugin/marketplace.json`** — Claude Code

No other project uses it yet

jgraphAGENTS.md

drawio-mcp / mcp-app-server

jgraph/drawio-mcp/mcp-app-server/AGENTS.md

MCP App Server Renders draw.io diagrams inline in AI chat interfaces using the MCP Apps protocol. ## Key Files | File | Purpose | |------|---------| | `src/shared.js` | Shared logic: `buildHtml()`, `processAppBundle()`, `createServer()` | | `src/index.js` | Node.js entry (Express

No other project uses it yet

jgraphAGENTS.md

drawio-mcp / mcp-tool-server

jgraph/drawio-mcp/mcp-tool-server/AGENTS.md

MCP Tool Server The original draw.io MCP server. Opens diagrams directly in the draw.io editor via browser. ## Key Files | File | Purpose | |------|---------| | `src/index.js` | Single-file server (stdio transport, vanilla

No other project uses it yet

jgraphAGENTS.md

drawio-mcp / project-instructions

jgraph/drawio-mcp/project-instructions/AGENTS.md

Project Instructions Alternative approach that works without installing the MCP server. Users add instructions to a Claude Project that teach Claude to generate draw.io URLs using Python code execution

No other project uses it yet

redisAGENTS.md

lettuce

redis/lettuce/AGENTS.md

Java, when available.** If a Java language server or IDE integration is present (e.g. an `jdtls`-based LSP, or an IDE MCP), use it for definitions, references, symbol/type search, call

No other project uses it yet

qybaiheAGENTS.md

bla

qybaihe/bla/AGENTS.md

rea-observability.ts`, `defense-score-honesty.ts`, and the `*-lint.ts` packaging / red-blue gates. - `src/mcp/server.ts`: JSON-RPC 2.0 MCP stdio server exposing 31 tools (full catalogue in `docs/cli-and-mcp.md`), including `bla_harden`, `bla_defend`, `bla_audit