How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
walter-graceDeletes or force-pushesCLAUDE.mdwalter-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.mdbeizhu-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.mdmarc-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
javedh-devCLAUDE.mdjavedh-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
NoOne-hubCLAUDE.mdNoOne-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.mdSterlingChin/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
SamuelQZQReads credentialsCLAUDE.mdSamuelQZQ/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
alumnium-hqCLAUDE.mdalumnium-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
AnthropicReads credentialsCLAUDE.mdanthropics/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.mdMadAppGang/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
jarrodwattsCLAUDE.mdjarrodwatts/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
spring-projectsCLAUDE.mdspring-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
desplega-aiReads credentialsCLAUDE.mddesplega-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
shanraisshanCLAUDE.mdshanraisshan/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
borgheiReads credentialsCLAUDE.mdborghei/Claude-Skills/CLAUDE.md
framework) + memory-tool/context-editing/reasoning-effort/caching upgrades to context-engine, llm-cost-optimizer, agent-workflow-designer, mcp-server-builder. Cross-platform surface unified — one `build_manifest.py` run regenerates `cli/skills.json`, `registry.json`, `.gemini/skills-index.json
borgheiCLAUDE.mdborghei/Claude-Skills/project-management/CLAUDE.md
1on1s/** - 1:1 templates by partner type (EM, designer, IC, manager) **Key Features:** - **Atlassian MCP Server** integration for direct Jira/Confluence operations - **Linear + Notion** integration patterns (GraphQL + REST) - **15+ Python
Pantheon-SecurityCLAUDE.mdPantheon-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.mddotCMS/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
rohitg00Reads credentialsCLAUDE.mdrohitg00/kubectl-mcp-server/CLAUDE.md
kubectl-mcp-server Project Memory ## Project Overview - **Name**: kubectl-mcp-server - **Version**: 2.0.0 - **Description**: Stateless MCP (2026-07-28) server for Kubernetes: 26 default tools (209 across all toolsets
marcantondahmenReads credentialsCLAUDE.mdmarcantondahmen/automad/.claude/CLAUDE.md
Inspector web UI against the local MCP endpoint (`http://localhost:8000/mcp`), authenticating with `AM_MCP_SERVER_TOKEN`/`AM_MCP_INSPECTOR_TOKEN` from `.env`. - `npm run mcp:tmp` — runs `bin/mcp-tmp.sh`, which
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
