How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
MicrosoftCLAUDE.mdmicrosoft/semanticworkbench/CLAUDE.md
Frontend work**: Study component patterns in `WORKBENCH_FRONTEND.md` * **API development**: Follow service patterns from `WORKBENCH_SERVICE.md` * **MCP servers**: Use existing servers in `MCP_SERVERS.md` as templates * **AI tools**: Provide relevant context files
ruilisiCLAUDE.mdruilisi/lsbot/CLAUDE.md
filtering:** ```bash gh issue list --repo owner/repo --json number,title --jq '.[] | "\(.number): \(.title)"' ``` ### /mcporter - MCP Server Management Use `mcporter` to work with MCP servers directly. **Quick start:** ```bash mcporter list
LangChainCLAUDE.mdlangchain-ai/langchain-google/CLAUDE.md
install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access. - **Contributing Guide:** [`.github/CONTRIBUTING.md`](https://docs.langchain.com/oss/python/contributing/overview) # Google
BlockRunAICLAUDE.mdBlockRunAI/blockrun-mcp/CLAUDE.md
BlockRun MCP MCP server giving Claude real-time data — markets, research, web search, crypto. Pay per call with USDC. ## Commands ```bash npm install # install dependencies npm run build # compile with
GRCEngClubCLAUDE.mdGRCEngClub/claude-grc-engineering/CLAUDE.md
Kubernetes**: kubectl, kubernetes SDK ## Issue tracking (Linear) This repo ships a **project-scoped** Linear MCP server in `.mcp.json` named `linear-grc-club`, pointing at `https://mcp.linear.app/mcp`. It loads only
aayushchCLAUDE.mdaayushch/laya/CLAUDE.md
else `--version` build id) instead of trusting the first PATH hit. **MCP** (`engine/laya/mcp/`): HTTP/SSE MCP server exposing Laya tools to external agents. Scope-filtered per user settings, space-aware
mrwoguCLAUDE.mdmrwogu/promptscript/CLAUDE.md
Commander.js - Testing: Vitest - Linting: ESLint + Prettier - Project: PromptScript ## Engineering Standards - Use code-review-graph MCP tools BEFORE Grep/Glob/Read when exploring the codebase - Exploring code: use semantic_search_nodes or query
openaccountantsCLAUDE.mdopenaccountants/openaccountants/CLAUDE.md
Load Guides from `packages/ /` (e.g. `packages/malta/`, `packages/us-ca/`) — each file is self-contained markdown. - Hosted MCP server for live, accountant-reviewed data: https://www.openaccountants.com/api/mcp - The website with the Tax Library
nwiizoCLAUDE.mdnwiizo/tfmcp/CLAUDE.md
CLAUDE.md tfmcp is a Rust-based MCP server for Terraform operations using the RMCP SDK. ## Quick Reference ```bash # Quality checks (run before commits) cargo fmt --all && RUSTFLAGS="-Dwarnings" cargo clippy
db-lyonCLAUDE.mddb-lyon/ue-mcp/CLAUDE.md
every contributor gets the same rulebook. ## Repo at a glance - **TS server** (`src/`) - the MCP server. Wraps the UE bridge over WebSocket, exposes 26 category tools with 1966+ actions
liangdabiaoCLAUDE.mdliangdabiao/Claude-Code-Stock-Deep-Research-Agent/CLAUDE.md
documents - `Task`: Deploy autonomous research agents - `TodoWrite`: Track research progress - `Skill`: Invoke specialized skills ### MCP Servers - `mcp__web_reader__webReader`: Enhanced web content extraction - `mcp__4_5v_mcp__analyze_image
ai-dashboadCLAUDE.mdai-dashboad/flutter-skill/CLAUDE.md
Barrel export - `lib/src/cli/` - CLI command implementations (launch, inspect, act, server, setup) - `lib/src/diagnostics/` - Error reporting - MCP Server mode (`cli/server.dart`) - JSON-RPC interface for IDEs like Cursor **Entry Points:** - `bin/flutter_skill.dart` - Main
OpenSource03CLAUDE.mdOpenSource03/harnss/CLAUDE.md
MentionPicker, EngineControls, │ │ # AttachmentPreview, ContextGauge, EnginePickerDropdown, useMentionAutocomplete) │ ├── jira/ # Jira board UI (KanbanBoard, JiraIssueCard, JiraBoardSetup) │ ├── mcp/ # MCP server management UI (AddServerDialog, McpServerRow, McpAuthStatus) │ ├── mcp-renderers/ # MCP tool renderers (jira, confluence, atlassian, context7
Kohei-WadaCLAUDE.mdKohei-Wada/taskdog/CLAUDE.md
taskdog-ui**: CLI (Click + Rich) and TUI (Textual), depends on core + client. - **taskdog-mcp**: MCP server for Claude Desktop (depends on client). **Communication**: CLI/TUI/MCP reach all data through the HTTP
obraCLAUDE.mdobra/superpowers-chrome/CLAUDE.md
MCP plugin. ## Project Structure ``` superpowers-chrome/ ├── package.json # Root package (version source of truth) ├── mcp/ # MCP server implementation │ ├── package.json # MCP-specific package (must match root version) │ ├── src/index.ts # TypeScript source │ └── dist/index.js # Bundled
ajsahniCLAUDE.mdajsahni/agents-office/CLAUDE.md
what to type. ## Changing the connectors The top bar shows the MCP servers **this machine's Claude Code** is connected to (`claude mcp list`). To add one: `claude mcp
receptronCLAUDE.mdreceptron/mulmoclaude/CLAUDE.md
centralized helpers - **Frontend → Server**: use `src/utils/api.ts` (`apiGet`, `apiPost`, etc.) — auto-attaches bearer token - **MCP → Server**: use `postJson()` with `AUTH_HEADER` - **Server → External**: use `AbortController` for timeouts, check `response.ok` ### Cross-platform
coleam00CLAUDE.mdcoleam00/remote-agentic-coding-system/.agents/examples/claude-telegram-bot/CLAUDE.md
else, when you see ANY task management scenario: 1. STOP and check if Archon MCP server is available 2. Use Archon task management as PRIMARY system 3. Refrain from using
jahalaCLAUDE.mdjahala/tilth/CLAUDE.md
tilth Rust MCP server + CLI for AST-aware code intelligence. Tree-sitter outlines, symbol search, callers/callees, file-level deps analysis. Replaces grep/cat/find for AI agents with structured, token-efficient output
LangChainCLAUDE.mdlangchain-ai/langchain-aws/CLAUDE.md
install and use file search tools for best results. If needed, use the docs MCP server as defined in `.mcp.json` for programmatic access. - **Contributing Guide:** [`.github/CONTRIBUTING.md`](https://docs.langchain.com/oss/python/contributing/overview) ## Important
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.
