A dedicated coding sub-agent for OpenClaw that handles background execution, test-driven bug fixing, and automated project scaffolding.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install coder-openclaw-agent
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 coder-openclaw-agent 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 Coder for OpenClaw?
Coder for OpenClaw is a specialized integration designed to streamline software development workflows by delegating coding tasks to a robust sub-agent. This skill provides a comprehensive toolkit including the workspace-coder prompt pack, a secure Docker-based sandbox, and a predefined orchestration contract. By integrating these Openclaw Skills, users can automate repetitive tasks like code verification and data analysis within a controlled environment.
This skill is essential for developers looking to scale their AI-assisted coding capabilities. It bridges the gap between high-level task delegation and low-level code execution, ensuring that the main agent remains focused on high-level strategy while the Coder sub-agent handles the technical implementation and verification steps.
Coder for OpenClaw Use Cases
- Automating background code execution and verification within a secure Docker sandbox.
- Executing test-driven edits and bug fixes without manual intervention.
- Rapid scaffolding of small projects and medium-scale data analysis tasks.
- Processing and extracting data from HTML, PDF, and office documents.
- Scaling AI development workflows using modular Openclaw Skills.
How Coder for OpenClaw Works
- The main OpenClaw agent identifies a coding or analysis requirement and delegates the task to the Coder sub-agent.
- The Coder agent initializes a secure environment based on the coder-sandbox Docker image.
- The sub-agent executes commands and scripts within the /tmp/coder/ directory to perform the requested task.
- Real-time verification is performed using Python or bash commands to ensure the code meets success criteria.
- The agent returns a structured JSON response to the main agent, reporting a status of SUCCESS, PARTIAL, or FAILURE.
Coder for OpenClaw Setup
Follow these steps to integrate the skill into your workflow:
- Clone the repository:
git clone https://github.com/MilleniumGenAI/coder-openclaw-agent.git
- Build the sandbox environment:
docker build -f docker/coder-sandbox.dockerfile -t coder-sandbox:latest .
- Copy the workspace files and register the agent in your openclaw.json file using the provided agent-config.template.json.
- Validate the installation:
openclaw models status --agent coder --probe --probe-provider openai-codex --json
Coder for OpenClaw Data Schema & Taxonomy
The Coder skill organizes its operational data and metadata through a strict hierarchy to ensure consistency across tasks.
| Component | Location/Format | Description |
|---|---|---|
| Source of Truth | SOUL.md | Defines the core logic and behavioral rules for the sub-agent. |
| Working Area | /tmp/coder/ |
The isolated directory where code execution and file generation occur. |
| Output Contract | Strict JSON | Returns deliverables including codeblocks, logs, and execution status. |
| Configuration | agent-config.json | Defines provider profiles and sandbox parameters. |
Coder for OpenClaw Advanced Features
- Support for complex multi-agent orchestration via the Main-to-Coder prompt alignment.
- Integrated sandbox log reporting for detailed debugging of failed execution states.
- Capability to handle blocked states gracefully using PARTIAL status updates.
- Pre-configured runtime inventory for consistent performance across different host environments.
- Extensible prompt packs that allow for fine-tuning of the sub-agent's coding style and constraints.
SKILL.md
Loading
Related Openclaw Skills
Plenty of Claws
A dating-style social network designed specifically for Clawdbot AI agents to create profiles and discover compatible matches.
Trends CLI Skill
A comprehensive AI skill for managing the @trends-fun/trends-skill-tool CLI to launch tokens, trade, and track earnings on the Solana blockchain.
Trends CLI
A professional command-line tool for deploying and trading memecoins on the trends.fun platform.
MoltHands
MoltHands is a task collaboration platform designed for AI agents to publish requirements, execute tasks, and manage incentives through a points-based system.
Smart Model Switching
A cost-saving routing system that automatically directs tasks to the most efficient Claude model tier based on task complexity.
Million Bit Homepage Minting Skill
An automated tool to mint images and links as permanent NFT plots on the Million Bit Homepage canvas on the Base blockchain.
Featured*
