A professional-grade programming integration that bridges the Claude Code CLI with OpenClaw for autonomous software engineering tasks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install claude-code-dev
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install claude-code-dev using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Claude Code Integration for OpenClaw?
This skill provides a robust integration between OpenClaw and the Claude Code CLI, allowing developers to execute complex programming workflows through messaging platforms or direct terminal commands. By leveraging Openclaw Skills, users can perform deep code analysis, autonomous bug fixing, and large-scale refactoring using Anthropic's most advanced models.
The integration supports two primary modes: the Agent Control Protocol (ACP) mode for persistent, interactive chat-based development, and the PTY mode for background execution and one-off tasks. This ensures that your AI agent is not just a chatbot but a functional engineering partner capable of managing file systems, running tests, and submitting git commits.
Claude Code Integration for OpenClaw Use Cases
- Autonomous bug fixing based on error logs or user descriptions
- Large-scale code refactoring and modernization (e.g., migrating to TypeScript or async/await)
- Generating comprehensive test suites and PR reviews directly from chat interfaces
- Executing non-interactive security audits and code analysis in CI/CD pipelines
- Managing complex project migrations with context-aware instruction via CLAUDE.md
How Claude Code Integration for OpenClaw Works
- The user initiates a programming task via an OpenClaw command or a natural language request in a bound chat thread.
- OpenClaw triggers the Claude Code CLI using either the ACP backend for interactive sessions or a PTY environment for background tasks.
- The skill identifies the project root and loads project-specific rules from the CLAUDE.md configuration file.
- Claude Code executes necessary shell commands, reads relevant source files, and iteratively applies code changes to solve the task.
- The system monitors token usage and budget limits in real-time, providing progress logs back to the user interface.
Claude Code Integration for OpenClaw Setup
To get started with this skill, ensure you have the Claude Code CLI installed and OpenClaw configured properly:
# Install the official Claude Code CLI
npm install -g @anthropic-ai/claude-code
# Set your API credentials
export ANTHROPIC_API_KEY="your_api_key_here"
# Install the acpx plugin for OpenClaw
openclaw plugins install acpx
openclaw config set plugins.entries.acpx.enabled true
# Configure the ACP backend
openclaw config set acp.enabled true
openclaw config set acp.backend acpx
openclaw config set plugins.entries.acpx.config.permissionMode approve-all
# Restart the gateway to apply changes
openclaw gateway restart
Claude Code Integration for OpenClaw Data Schema & Taxonomy
The skill utilizes a combination of environment variables and local configuration files to manage state and project context:
| Component | Type | Description |
|---|---|---|
| CLAUDE.md | Markdown | Project-specific coding standards, tech stack info, and constraints automatically read on startup. |
| Session ID | String | Unique identifier for tracking background PTY processes. |
| JSON Output | Object | Structured data format for non-interactive analysis modes. |
| ACP Bindings | Metadata | Maps specific chat threads (Discord/Telegram) to active Claude Code sessions. |
Claude Code Integration for OpenClaw Advanced Features
- Model tiering strategy: Use Sonnet 3.5 for standard coding and switch to Opus for high-level architectural decisions to optimize Openclaw Skills performance.
- Budget Safeguards: Set hard limits on session spending using the --max-budget-usd flag to prevent runaway costs.
- Context Compression: Use the /compact command during long sessions to summarize history and save on input tokens.
- AWS Bedrock Support: Seamlessly switch from the Anthropic API to AWS Bedrock for enterprise-grade infrastructure and cost management.
- Persistent Threading: Bind specific chat channels directly to a workspace for continuous, multi-day development sessions.
SKILL.md
Loading
Related Openclaw Skills
Memory Dream
Memory Dream is a structured memory classification and periodic consolidation system designed to keep Openclaw Skills agents efficient and context-aware.
voice-minimax
A professional integration that converts text into natural speech using MiniMax TTS and delivers it as voice messages or files to Lark via lark-cli.
Complex Task Orchestrator
A robust framework for decomposing, executing, and recovering complex, multi-step AI agent tasks without losing context or data.
Skill Sync
A powerful utility to audit, deduplicate, and synchronize AI agent skills across multiple environments into a single canonical source of truth.
Skill Index
An automated inventory management tool that scans, categorizes, and indexes your entire collection of Openclaw Skills.
Skill State Manager (SSM)
A Meta Skill that automates API key management and state persistence through native conversational prompts for AI agents.
Featured*
