A powerful orchestration skill that delegates complex, multi-file coding tasks to specialized AI agents like Claude Code and Codex with background monitoring and safe review workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-coding-agent-workflows
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 openclaw-coding-agent-workflows 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 Coding Agent?
The Coding Agent skill is a high-performance orchestration layer designed for the Openclaw Skills ecosystem. it allows developers to offload significant engineering efforts—such as feature implementation, large-scale refactors, and issue triage—to industry-leading AI models including Codex, Claude Code, Pi, and OpenCode. By utilizing this skill, users can manage parallel workstreams from the command line while maintaining strict control over execution environments.
Built for reliability, this skill handles the nuances of different agent interfaces, such as PTY requirements for interactive shells and bypass permissions for automated flows. It bridges the gap between simple code generation and full-scale autonomous engineering, making it a cornerstone of the Openclaw Skills suite for professional DevOps and development pipelines.
Coding Agent Use Cases
- Implementing complex features that require simultaneous edits across multiple files and directories.
- Executing large-scale architectural refactors where parallel workstreams increase velocity.
- Performing secure PR reviews and issue triage within isolated git worktrees or temporary clones.
- Running automated 'run-fix-verify' loops in the background to ensure code quality without manual intervention.
How Coding Agent Works
- The user defines a coding task with a specific scope, constraints, and required validation checks.
- Openclaw Skills identifies the appropriate agent (Codex, Claude, etc.) and initializes the required execution mode, such as PTY for interactive agents.
- The skill establishes a session in a designated working directory, ensuring repository isolation for safety.
- If background execution is enabled, the agent runs the task while the user monitors progress via session logs and polling.
- Upon completion or blocker identification, the agent provides a summary of changes and test outcomes, often triggering a system event to notify the user.
Coding Agent Setup
To use the Coding Agent skill, ensure you have at least one supported agent binary installed. Use the following bash commands to initiate sessions:
# Install the necessary agent (example: Claude Code)
npm install -g @anthropic-ai/claude-code
# Run a task using Openclaw Skills syntax
bash pty:true workdir:~/my-repo command:"codex exec --full-auto 'Refactor API middleware'"
Coding Agent Data Schema & Taxonomy
The skill manages data through session-based isolation and standard output streams. It adheres to the following structure:
| Component | Type | Description |
|---|---|---|
workdir |
Path | The isolated directory (repo or worktree) where edits occur. |
sessionId |
String | A unique identifier for background process monitoring. |
pty |
Boolean | Determines if a pseudo-terminal is allocated for interactive agents. |
logs |
Stream | Captured output from the coding agent for review and debugging. |
Coding Agent Advanced Features
- Background Session Monitoring: Start long-running tasks and use
process action:polloraction:logto track progress asynchronously. - Isolated Review Workflows: Built-in support for
mktempandgit worktreeto prevent accidental changes to live production code. - Failure Recovery Loops: Intelligent checklists for stalling output or early session termination, including relaunching with tighter prompt scopes.
- Custom Prompt Templates: Standardized task structures that enforce reporting of changed files and linting outcomes.
SKILL.md
Loading
Related Openclaw Skills
CI/CD Pipeline Toolkit
An automated CI/CD pipeline management tool supporting GitHub Actions, GitLab CI, and Jenkins to streamline build, test, and deployment workflows.
Editor in Hindi
A powerful AI skill that automates Hindi video editing, captions, and subtitle generation through simple natural language instructions.
Upload Video - AI Video Processing
A powerful AI video editing skill for uploading raw footage, applying automated edits via cloud GPUs, and exporting high-quality 1080p MP4 files.
Movie Maker Chromebook Free
A cloud-powered AI video editing skill that allows Chromebook users to trim, combine, and export 1080p MP4 videos without local software installation.
Hermes Memory System
A self-driven memory management system for AI agents modeled after the Hermes architecture to ensure long-term memory health and efficiency.
Video Object
A sophisticated AI video agent skill that automates object tracking and highlights in video clips using remote GPU rendering and natural language commands.
Featured*
