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.
szTheoryCLAUDE.mdszTheory/exifcleaner/CLAUDE.md
with `--remote-debugging-port=9222`) 2. Claude Code connects via the `chrome-devtools` MCP server to read console logs, take screenshots, evaluate JS MCP config is in `.claude.json` (project-scoped
jgravelleReads credentialsCLAUDE.mdjgravelle/jcodemunch-mcp/CLAUDE.md
jcodemunch-mcp — Project Brief ## Current State - **Version:** 1.108.402 — **the server instructions name the tools in the first 512 characters, and tool names hold across 1.x** (#1248, #1247, #1246): ToolSearch
tradermontyReads credentialsCLAUDE.mdtradermonty/claude-trading-skills/CLAUDE.md
your_secret_key" export ALPACA_PAPER="true" # or "false" for live trading # Configure Alpaca MCP Server in Claude Code settings # See portfolio-manager/references/alpaca-mcp-setup.md for detailed setup guide ``` #### API Pricing
Steady8 mentions in 2 weeks
No other project uses it yet
chrisryugjReads credentialsCLAUDE.mdchrisryugj/korean-law-mcp/CLAUDE.md
이미지로 덮어써 stats·patent·archhub·school까지 전부 죽는다. 자세한 배경: [docs/FLY-COST.md](docs/FLY-COST.md) Korean Law MCP Server v4.15.21 - 법제처 42개 API → 10개 통합 도구 (내부 100개) + 9개 시나리오 + 자연어 CLI + HTTP
Hugging FaceCLAUDE.mdhuggingface/OpenEnv/CLAUDE.md
boundary**: WebSocket for infrastructure (Gym-like API), MCP for agents - **Rewards inside environment**: Domain knowledge encapsulated in environment, not external - **Client-server separation**: Clients never import from `server/` directory ## Simplicity
overwirehqReads credentialsCLAUDE.mdoverwirehq/claude-code-telegram/CLAUDE.md
separated Telegram IDs), `ANTHROPIC_API_KEY`, `ENABLE_MCP`, `MCP_CONFIG_PATH`. Agentic platform settings: `AGENTIC_MODE` (default true), `ENABLE_API_SERVER`, `API_SERVER_PORT` (default 8080), `GITHUB_WEBHOOK_SECRET`, `WEBHOOK
themesbergCLAUDE.mdthemesberg/flowbite-svelte/CLAUDE.md
Flowbite-Svelte MCP server, where you have access to comprehensive Flowbite-Svelte component documentation. Here's how to use the available tools effectively: ## Available MCP Tools: ### 1. findComponent Use this
mattermostReads credentialsCLAUDE.mdmattermost/mattermost-mobile/CLAUDE.md
features that require mobile device interaction: - **Use subagents**: Launch a subagent to handle mobile MCP testing to avoid excessive context usage - The subagent can launch the app, navigate, take screenshots
jeremylongshoreReads credentialsCLAUDE.mdjeremylongshore/tons-of-skills-marketplace/CLAUDE.md
category]/[name]/`): `.claude-plugin/plugin.json` + `README.md` + optional `commands/*.md`, `agents/*.md`, `skills/[name]/SKILL.md`. **MCP server plugins** (`plugins/mcp/[name]/`): TypeScript source in `src/`, built to `dist/index.js` (must be executable: shebang
No other project uses it yet
centminmodCLAUDE.mdcentminmod/my-claude-code-setup/CLAUDE.md
setup - Description: Template repository providing CLAUDE.md templates, memory bank system, hooks, skills, subagents, and MCP server configurations for Claude Code projects - This is a template repo — no application code. Users
fabio-rovaiCLAUDE.mdfabio-rovai/open-ontologies/CLAUDE.md
Claude adds them. The MCP tools are individual operations — Claude is the orchestrator. ## Tool Reference | Tool | When to use | | ---- | ----------- | | `onto_status` | To check if the server is running and healthy
Agent-FieldReads credentialsCLAUDE.mdAgent-Field/agentfield/CLAUDE.md
Standalone server binary **Core Packages (`internal/`):** - `cli/` - CLI command definitions and routing - `server/` - HTTP server setup (Gin framework), middleware, routing - `handlers/` - HTTP request handlers for REST/gRPC endpoints - `services/` - Business logic
Steady4 mentions in 2 weeks
No other project uses it yet
southleftReads credentialsCLAUDE.mdsouthleft/figma-console-mcp/CLAUDE.md
Figma Console MCP The most comprehensive MCP server for Figma — design tokens, components, variables, and programmatic design creation. ## Build & Test ```bash npm run build # Compiles local + cloudflare + apps
No other project uses it yet
oxsecurityCLAUDE.mdoxsecurity/megalinter/CLAUDE.md
from [DataDog/datadog-api-claude-plugin](https://github.com/DataDog/datadog-api-claude-plugin) (New Relic publishes no official agent skill, only an MCP server) ## Rules Context-aware rules in `.claude/rules/` are automatically loaded based on which files
Steady3 mentions in 2 weeks
No other project uses it yet
David-CrtyReads credentialsCLAUDE.mdDavid-Crty/databasement/CLAUDE.md
same server (e.g., rollback) - Both services handle MySQL, MariaDB, and PostgreSQL with appropriate SSL/connection handling ### Actions An operation that more than one edge performs (Livewire, REST API, MCP, console/scheduler, agent
Nano-CollectiveCLAUDE.mdNano-Collective/nanocoder/CLAUDE.md
security disclaimer for new directories 2. **App Initialization** (`useAppInitialization`) - Creates LLM client, loads MCP servers, loads custom commands 3. **Central State** (`useAppState`) - Single source of truth for 50+ state variables
No other project uses it yet
openwebfCLAUDE.mdopenwebf/webf/CLAUDE.md
source product requiring subscription: ```yaml dependencies: webf: ^0.23.10 # Enterprise version available on pub.dev ``` ## 📊 WebF MCP Server The MCP server provides dependency graph analysis: ### Key Features - 8,244+ nodes across multiple
sandbox-quantumReads credentialsCLAUDE.mdsandbox-quantum/switch/CLAUDE.md
replies posted on its behalf) - `bridges/` — External integrations - `agent/` — Agent Bridge (HTTP API, MCP server); `protocol/agent_core.py` is `AgentCore`, `protocol/agent_connections.py` holds each `AgentConnection` - `collaboration/` — Collaboration Bridge: one `CollaborationCore` per workspace, driving
redhat-etCLAUDE.mdredhat-et/ripwire/CLAUDE.md
core sits the verb catalog in `docs/COMMANDS.md` — navigation, diff-awareness, quality, retrieval — and an MCP server so an agent can call them mid-task. ## Where to look | Question | File | | --- | --- | | What
Steady5 mentions in 2 weeks
No other project uses it yet
antonbabenkoCLAUDE.mdantonbabenko/terraform-skill/CLAUDE.md
from SKILL.md) — CI-owned, never hand-edit ├── mcp.json # Optional Kiro MCP (read-only terraform-mcp-server) ├── tests/ # Baseline scenarios and rationalization tracking │ ├── baseline-scenarios.md │ ├── compliance-verification.md │ └── rationalization-table.md └── .github/ ├── release/ │ ├── pre-commit.js # Release version
Steady5 mentions in 2 weeks
No other project uses it yet
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.
