CLAUDE.md examples from real projects

javedh-devCLAUDE.md

tracktor

javedh-dev/tracktor/CLAUDE.md

/code) when working with code in this repository. ## Svelte MCP Usage Use the Svelte MCP server for any Svelte, SvelteKit, or `.svelte`/`.svelte.ts` work: 1. **`list-sections`** — call first

ruby-uiCLAUDE.md

ruby_ui

ruby-ui/ruby_ui/CLAUDE.md

claude/skills/shadcn-audit/`](.claude/skills/shadcn-audit/) (audit a PR/component) and [`.claude/skills/shadcn-drift/`](.claude/skills/shadcn-drift/) (weekly upstream watch). | | [`mcp/`](mcp/) | MCP server for ruby_ui; `mcp/data/registry/` (one JSON per component plus `index.json`) is generated from

am-willCLAUDE.md

codex-skills

am-will/codex-skills/CLAUDE.md

skill`, `read-github`) - Fetch up-to-date library docs - Query documentation via APIs or MCP servers - Convert URLs to LLM-friendly formats 3. **Domain expertise skills** (`frontend-design`, `frontend-responsive

walter-graceDeletes or force-pushesCLAUDE.md

mac-code

walter-grace/mac-code/CLAUDE.md

Real-time server monitor (tok/s, slots, memory) - `config.example.json` — PicoClaw config with DuckDuckGo search + fetch MCP servers - `setup.sh` — One-command install script (alternative to manual steps) ## Architecture Two models, one agent

beizhu-1209Reads credentialsCLAUDE.md

AIHelms

beizhu-1209/AIHelms/CLAUDE.md

Overview AIHelms is an enterprise AI resource management platform that unifies model, Skill, and MCP Server management with enterprise AI identity. ## Tech Stack | Layer | Technology | |-------|-----------| | Backend | Python 3.11+, FastAPI, Gunicorn

marc-shadeReads credentialsCLAUDE.md

world-intel-mcp

marc-shade/world-intel-mcp/CLAUDE.md

claude.ai/code) when working with code in this repository. ## What This Is World Intelligence MCP Server: 160 tools across 30+ domains providing real-time global intelligence from free public APIs

desplega-aiReads credentialsCLAUDE.md

agent-swarm

desplega-ai/agent-swarm/CLAUDE.md

PATH`, use `uvx --from "semble[mcp]" semble` in its place. If the `semble` MCP server is enabled, prefer its `search` / `find_related` tools over the CLI. To keep search output

NoOne-hubCLAUDE.md

JSReverser-MCP

NoOne-hub/JSReverser-MCP/CLAUDE.md

format npm run format # Check formatting without fixing npm run check-format # Start the MCP server (builds first) npm run start # Start with debug logging npm run start-debug # Generate

SterlingChinReads credentialsCLAUDE.md

marvin-template

SterlingChin/marvin-template/CLAUDE.md

rules and domain logic. See `docs/patterns/cli-integration.md` for how to wrap CLIs as skills. 2. **MCP servers** - For tools without CLIs. Configure via Claude Code's MCP system. 3. **Custom scripts

alumnium-hqCLAUDE.md

alumnium

alumnium-hq/alumnium/CLAUDE.md

replay for host agents: agent-neutral `Recording` schema, `Masker`, `Recorder` sink and `TestCache`/`FileTestCache` - `server/`, `mcp/`, `cli/` - HTTP server, MCP server and CLI, only shipped inside the compiled `alumnium` binary

SamuelQZQReads credentialsCLAUDE.md

auto-coding-agent-demo

SamuelQZQ/auto-coding-agent-demo/CLAUDE.md

development server at http://localhost:3000 **DO NOT skip this step.** Ensure the server is running before proceeding. ### Step 2: Select Next Task Read `task.json` and select ONE task

AnthropicReads credentialsCLAUDE.md

launch-your-agent

anthropics/launch-your-agent/CLAUDE.md

patterns + typical endpoint schemas — so v1 is just the swap to the real MCP server + vault. - **Voice**: warm welcome, no clinical process talk, no time estimates or unverified durations; compact/dense

MadAppGangReads credentialsCLAUDE.md

claudish

MadAppGang/claudish/CLAUDE.md

json` (a VALID one is applied correctly); why magmux, and the one `-p` the MCP server does start (`run_prompt` on a Claude model) - `pane-session.md` — MCP and CLI `team` slots

No other project uses it yet

jarrodwattsCLAUDE.md

claude-delegator

jarrodwatts/claude-delegator/CLAUDE.md

uninstall to test removal flow /claude-delegator:uninstall ``` No build step, no dependencies. Uses native MCP servers from Codex and Gemini CLIs. ## Architecture ### Orchestration Flow Claude acts as orchestrator—delegates

Get-Concord-AICLAUDE.md

concord-mcp

Get-Concord-AI/concord-mcp/CLAUDE.md

Read it before making changes. ## What this project is `concord-mcp` is a local MCP server plus a `concord` CLI that gives coding agents shared work-state: agents **register their

spring-projectsCLAUDE.md

spring-tools

spring-projects/spring-tools/CLAUDE.md

Boot extensions ├── nodejs-packages/ # Shared Node.js utilities └── claude-plugins/ # Claude Code plugin (standalone LS + MCP server) ├── spring-tools/ # Plugin source (skills, hooks, explanations/ .md playbooks) ├── tools/ # Node.js checker + tests keeping

flamingo-stackCLAUDE.md

openframe-oss-lib / openframe-frontend-core

flamingo-stack/openframe-oss-lib/openframe-frontend-core/CLAUDE.md

generating code from Figma MCP output, but also to all hand-written styles. Figma MCP returns React+Tailwind with raw hex colors, pixel sizes, and font shorthands — that output

No other project uses it yet

shanraisshanCLAUDE.md

codex-cli-best-practice

shanraisshan/codex-cli-best-practice/CLAUDE.md

Config** (`.codex/config.toml`) — TOML-based layered config with 5 profiles (conservative, development, trusted, ci, review), MCP server registration, and agent definitions. Project-level overrides user-level (`~/.codex/config.toml`); CLI flags override both

Pantheon-SecurityCLAUDE.md

medusa

Pantheon-Security/medusa/CLAUDE.md

Security MEDUSA scans with 40,000+ built-in patterns for: - AI/ML applications, LLM agents, MCP servers - Prompt injection, RAG poisoning, agent security - Traditional vulnerabilities (SQL injection, XSS, secrets) - Configuration files

dotCMSCLAUDE.md

core / core-web

dotCMS/core/core-web/CLAUDE.md

attack: check that version's publish date and provenance history before adding a line. ### MCP Servers Configured in `/.mcp.json`. Use these instead of guessing: - **`angular-cli`** — Angular best practices, documentation