claude-delegator
starsforks
How to install claude-delegator?
jarrodwatts/claude-delegator
$git clone https://github.com/jarrodwatts/claude-delegatorGPT expert subagents for Claude Code. Five specialists that can analyze AND implement—architecture, security, code review, and more.
README.md
| 1 | # Claude Delegator |
| 2 | |
| 3 | GPT expert subagents for Claude Code. Five specialists that can analyze AND implement—architecture, security, code review, and more. |
| 4 | |
| 5 | [](LICENSE) |
| 6 | [](https://github.com/jarrodwatts/claude-delegator/stargazers) |
| 7 | |
| 8 |  |
| 9 | |
| 10 | ## Install |
| 11 | |
| 12 | Inside a Claude Code instance, run the following commands: |
| 13 | |
| 14 | **Step 1: Add the marketplace** |
| 15 | ``` |
| 16 | /plugin marketplace add jarrodwatts/claude-delegator |
| 17 | ``` |
| 18 | |
| 19 | **Step 2: Install the plugin** |
| 20 | ``` |
| 21 | /plugin install claude-delegator |
| 22 | ``` |
| 23 | |
| 24 | **Step 3: Run setup** |
| 25 | ``` |
| 26 | /claude-delegator:setup |
| 27 | ``` |
| 28 | |
| 29 | Done! Claude now routes complex tasks to GPT experts automatically. |
| 30 | |
| 31 | > **Note**: Requires [Codex CLI](https://github.com/openai/codex) or [Gemini CLI](https://github.com/google/gemini-cli). Setup guides you through installation. |
| 32 | |
| 33 | --- |
| 34 | |
| 35 | ## What is Claude Delegator? |
| 36 | |
| 37 | Claude gains a team of GPT and Gemini specialists via native MCP. Each expert has a distinct specialty and can advise OR implement. |
| 38 | |
| 39 | **Note:** You can use either provider (GPT or Gemini), or both. The plugin will automatically detect which one is configured and route tasks accordingly. |
| 40 | |
| 41 | | What You Get | Why It Matters | |
| 42 | |--------------|----------------| |
| 43 | | **5 domain experts** | Right specialist for each problem type | |
| 44 | | **GPT or Gemini** | Use your preferred model provider | |
| 45 | | **Dual mode** | Experts can analyze (read-only) or implement (write) | |
| 46 | | **Auto-routing** | Claude detects when to delegate based on your request | |
| 47 | | **Synthesized responses** | Claude interprets expert output, never raw passthrough | |
| 48 | |
| 49 | ### The Experts |
| 50 | |
| 51 | | Expert | What They Do | Example Triggers | |
| 52 | |--------|--------------|------------------| |
| 53 | | **Architect** | System design, tradeoffs, complex debugging | "How should I structure this?" / "What are the tradeoffs?" | |
| 54 | | **Plan Reviewer** | Validate plans before you start | "Review this migration plan" / "Is this approach sound?" | |
| 55 | | **Scope Analyst** | Catch ambiguities early | "What am I missing?" / "Clarify the scope" | |
| 56 | | **Code Reviewer** | Find bugs, improve quality | "Review this PR" / "What's wrong with this?" | |
| 57 | | **Security Analyst** | Vulnerabilities, threat modeling | "Is this secure?" / "Harden this endpoint" | |
| 58 | |
| 59 | ### When Experts Help Most |
| 60 | |
| 61 | - **Architecture decisions** — "Should I use Redis or in-memory caching?" |
| 62 | - **Stuck debugging** — After 2+ failed attempts, get a fresh perspective |
| 63 | - **Pre-implementation** — Validate your plan before writing code |
| 64 | - **Security concerns** — "Is this auth flow safe?" |
| 65 | - **Code quality** — Get a second opinion on your implementation |
| 66 | |
| 67 | ### When NOT to Use Experts |
| 68 | |
| 69 | - Simple file operations (Claude handles these directly) |
| 70 | - First attempt at any fix (try yourself first) |
| 71 | - Trivial questions (no need to delegate) |
| 72 | |
| 73 | --- |
| 74 | |
| 75 | ## How It Works |
| 76 | |
| 77 | ``` |
| 78 | You: "Is this authentication flow secure?" |
| 79 | ↓ |
| 80 | Claude: [Detects security question → selects Security Analyst] |
| 81 | ↓ |
| 82 | ┌───────────────────────────────┐ |
| 83 | │ mcp__codex__codex │ |
| 84 | │ (or mcp__gemini__gemini) │ |
| 85 | │ → Security Analyst prompt │ |
| 86 | │ → Expert analyzes your code │ |
| 87 | └───────────────────────────────┘ |
| 88 | ↓ |
| 89 | Claude: "Based on the analysis, I found 3 issues..." |
| 90 | [Synthesizes response, applies judgment] |
| 91 | ``` |
| 92 | |
| 93 | **Key details:** |
| 94 | - Each expert has a specialized system prompt (in `prompts/`) |
| 95 | - Claude reads your request → picks the right expert → delegates via MCP (GPT or Gemini) |
| 96 | - Responses are synthesized, not passed through raw |
| 97 | - Experts can retry up to 3 times before escalating |
| 98 | - Multi-turn conversations preserve context via `threadId` for chained tasks |
| 99 | |
| 100 | ### Multi-Turn Conversations |
| 101 | |
| 102 | For chained implementation steps, the expert preserves context across turns: |
| 103 | |
| 104 | ``` |
| 105 | Turn 1: mcp__*__* → returns threadId |
| 106 | Turn 2: mcp__*__*-reply(threadId) → expert |
People who liked this also viewed
6 picksType
- fastapi_mcpExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!MCP ServersNov 2025
- lean-lsp-mcpLean Theorem Prover MCPMCP ServersJul 2026
- rulesyncA Utility CLI for AI Coding AgentsMCP ServersJul 2026
- FunASROpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.MCP ServersJul 2026
- repomix📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.MCP ServersJul 2026
- mcp-serverMCP server for AI-assisted development of CAP applicationsMCP ServersJul 2026
