claude-delegator

GPT expert subagents for Claude Code. Five specialists that can analyze AND implement—architecture, security, code review, and more.

 

!Claude Delegator in action

Install

Inside a Claude Code instance, run the following commands:

Step 1: Add the marketplace

/plugin marketplace add jarrodwatts/claude-delegator

Step 2: Install the plugin

/plugin install claude-delegator

Step 3: Run setup

/claude-delegator:setup

Done! Claude now routes complex tasks to GPT experts automatically.

Note: Requires Codex CLI or Gemini CLI. Setup guides you through installation.

What is Claude Delegator?

Claude gains a team of GPT and Gemini specialists via native MCP. Each expert has a distinct specialty and can advise OR implement.

Note: You can use either provider (GPT or Gemini), or both. The plugin will automatically detect which one is configured and route tasks accordingly.

The Experts

When Experts Help Most

• •Architecture decisions — "Should I use Redis or in-memory caching?"
• •Stuck debugging — After 2+ failed attempts, get a fresh perspective
• •Pre-implementation — Validate your plan before writing code
• •Security concerns — "Is this auth flow safe?"
• •Code quality — Get a second opinion on your implementation

When NOT to Use Experts

• •Simple file operations (Claude handles these directly)
• •First attempt at any fix (try yourself first)
• •Trivial questions (no need to delegate)

How It Works

You: "Is this authentication flow secure?"
                    ↓
Claude: [Detects security question → selects Security Analyst]
                    ↓
        ┌───────────────────────────────┐
        │  mcp__codex__codex            │
        │  (or mcp__gemini__gemini)     │
        │  → Security Analyst prompt    │
        │  → Expert analyzes your code  │
        └───────────────────────────────┘
                    ↓
Claude: "Based on the analysis, I found 3 issues..."
        [Synthesizes response, applies judgment]

Key details:

• •Each expert has a specialized system prompt (in prompts/)
• •Claude reads your request → picks the right expert → delegates via MCP (GPT or Gemini)
• •Responses are synthesized, not passed through raw
• •Experts can retry up to 3 times before escalating
• •Multi-turn conversations preserve context via threadId for chained tasks

Multi-Turn Conversations

For chained implementation steps, the expert preserves context across turns:

Turn 1: mcp__*__* → returns threadId
Turn 2: mcp__*__*-reply(threadId) → expert remembers turn 1
Turn 3: mcp__*__*-reply(threadId) → expert remembers turns 1-2

Use single-shot (codex or gemini only) for advisory tasks. Use multi-turn for implementation chains and retries.

Configuration

Operating Modes

Every expert supports two modes based on the task:

Claude automatically selects the mode based on your request.

Configuration Defaults

Set global defaults in ~/.codex/config.toml instead of passing parameters on every call:

sandbox_mode = "workspace-write"
approval_policy = "on-failure"

Per-call parameters override these defaults. See Codex CLI docs for all config options.

Manual MCP Setup

If /setup doesn't work, register the MCP server(s) manually:

# For Codex (GPT)
# Idempotent: safe to rerun
claude mcp remove codex >/dev/null 2>&1 || true
claude mcp add --transport stdio --scope user codex -- codex -m gpt-5.3-codex mcp-server

# For Gemini
# Idempotent: safe to rerun
claude mcp remove gemini >/dev/null 2>&1 || true
claude mcp add --transport stdio --scope user gemini -- node ${CLAUDE_PLUGIN_ROOT}/server/gemini/index.js

Verify with:

claude mcp list
printf '{"jsonrpc":"2.0","id":"health","method":"initialize","params":{}}\n' | node ${CLAUDE_PLUGIN_ROOT}/server/gemini/index.js

Customizing Expert Prompts

Expert prompts live in prompts/. Each follows the same structure:

• •Role definition and context
• •Advisory vs Implementation modes
• •Response format guidelines
• •When to invoke / when NOT to invoke

Edit these to customize expert behavior for your workflow.

Requirements

You need at least one of the following providers configured:

• •Codex CLI (for GPT): npm install -g @openai/codex
• •Gemini CLI (for Gemini): npm install -g @google/gemini-cli

Authentication:

• •Codex: run codex login
• •Gemini: run gemini once and complete the sign-in flow (or set GOOGLE_API_KEY)

Commands

Troubleshooting

Development

git clone https://github.com/jarrodwatts/claude-delegator
cd claude-delegator

# Test locally without reinstalling
claude --plugin-dir /path/to/claude-delegator

See CONTRIBUTING.md for guidelines.

Acknowledgments

Expert prompts adapted from oh-my-opencode by @code-yeongyu.

License

MIT — see LICENSE

Star History