claude-code-delegate

# Claude Code Delegate

Delegate programming tasks to local Claude Code CLI.

**RULE: You NEVER write code directly. ALL programming goes through `claude -p`.**

## Prerequisites Check (Run Before First Use)

Before delegating any task, verify the environment is ready:

1. **Claude Code CLI installed**: Run `which claude` — if not found, tell user: `npm install -g @anthropic-ai/claude-code`
2. **API key configured**: Run `claude --version` — if it errors about auth, tell user to run `claude` and complete login
3. **Write-guard active (STRONGLY RECOMMENDED)**: Check if a write-guard plugin exists at `.openclaw/extensions/write-guard/`. If not, warn the user:
   > ⚠️ No write-guard detected. The delegate uses `--permission-mode bypassPermissions` which grants full filesystem read/write access. It is strongly recommended to set up a write-guard plugin before running tasks. See README.md for setup instructions.

Only proceed with delegation after items 1 and 2 pass. Item 3 is a warning — the user may choose to proceed without it, but should be informed of the risk.

## When to Trigger

Auto-trigger on ANY of these:
- Write, modify, refactor, debug code
- Create project files or directories
- Run tests, lint, build
- Code review, architecture planning
- Edit any file (except memory/ and .relationship/)

Manual trigger: user sends `/code <task>`

Do NOT trigger: chat, emotional interaction, information lookup.

## Command Template

```bash
cd "<project_dir>" && claude -p "<task_description>" --output-format text --max-turns 10 --permission-mode bypassPermissions
```

### Parameters

| Param | Purpose | Required |
|-------|---------|----------|
| `-p` | Non-interactive mode | Yes |
| `cd "<dir>" &&` | Set working dir (no --cwd flag exists) | Yes |
| `--output-format text` | Plain text output | Recommended |
| `--max-turns 10` | Limit execution rounds | Recommended |
| `--permission-mode bypassPermissions` | Auto-accept file edits (**requires write-guard**, see Prerequisite...

# 🔧 Claude Code Delegate

**An OpenClaw skill that delegates programming tasks to a local Claude Code CLI instance.**

Your OpenClaw agent handles conversation and user interaction. When coding is needed, it delegates to Claude Code (`claude -p`) running locally — giving your agent professional-grade programming ability without the main agent writing code directly.

## Why Delegate?

| Without Delegation | With Delegation |
|---|---|
| Main agent writes code inline (often poor quality) | Claude Code handles all programming with full tooling |
| Agent gets stuck in long code blocks, loses conversation context | Agent stays responsive, code runs async in background |
| No file system awareness | Full file system access, can run tests, install packages |
| Single-model limitations | Leverages Claude Code's specialized coding abilities |

## How It Works

```
User: "Write me a stock screener in Python"
    ↓
Main Agent: delegates via `claude -p "Write a stock screener in projects/screener/"`
    ↓
Main Agent: immediately replies "On it! Let me get that done for you."
    ↓
Claude Code: writes files, installs deps, runs tests (async, non-blocking)
    ↓
User: (sends next message)
    ↓
Main Agent: polls for result, relays summary with personality
```

## Installation

```bash
npx clawhub install claude-code-delegate
```

Or manually copy the skill directory into your workspace's `skills/` folder.

### Prerequisites

- [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) installed locally:
  ```bash
  npm install -g @anthropic-ai/claude-code
  ```
- **`ANTHROPIC_API_KEY`** environment variable set, or Claude Code authenticated via `claude` login
- [OpenClaw](https://github.com/openclaw/openclaw) agent framework
- **Write-guard plugin (strongly recommended)** — See [Security Notes](#%EF%B8%8F-security-notes) below. This skill uses `--permission-mode bypassPermissions` which grants the delegate full filesystem access. Without a write-guard, the delegate can re...