Code Cog OpenClaw Skill

The first coding agent designed for agents, not just humans. Code generation, debugging, refactoring, codebase exploration, terminal operations — directly on...

v1.0.3 Recently Updated Updated Today

Installation

clawhub install code-cog

Requires npm i -g clawhub

63

Downloads

0

Stars

1

current installs

1 all-time

4

Versions

EU EU-Hosted Inference API

Power your OpenClaw skills with the best open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

Explore Inference API

GLM

GLM 5

$1.00 / $3.20

per M tokens

Kimi

Kimi K2.5

$0.60 / $2.80

per M tokens

MiniMax

MiniMax M2.5

$0.30 / $1.20

per M tokens

Qwen

Qwen3.5 122B

$0.40 / $3.00

per M tokens

Code Cog - The First Coding Agent Designed for Agents

A coding sub-agent that works directly on your machine — understands the codebase, plans changes, and iterates until the code works.


Prerequisites

This skill requires the cellcog skill for SDK setup and API calls, plus CellCog Desktop (Co-work) for machine access.

clawhub install cellcog
clawhub install cowork-cog  # Setup guide for CellCog Desktop

Read the cellcog skill first for SDK setup. This skill shows you what's possible.

OpenClaw agents (fire-and-forget — recommended for long tasks):

result = client.create_chat(
    prompt="[your task prompt]",
    notify_session_key="agent:main:main",
    task_label="my-task",
    chat_mode="agent core",  # Lightweight context for coding
    enable_cowork=True,
    cowork_working_directory="/path/to/project",
)

All other agents (blocks until done):

result = client.create_chat(
    prompt="[your task prompt]",
    task_label="my-task",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/path/to/project",
)

See the cellcog mothership skill for complete SDK API reference.


What CellCog Has Internally

  1. Direct Machine Access — Terminal commands and file operations executed on the user's actual machine via CellCog Desktop bridge.
  2. Codebase Understanding — Reads project structure, AGENTS.md/README.md, and explores files before making changes.
  3. Iterative Execution — Plans multi-file changes, executes, tests, and self-corrects through agent threads.
  4. Multimedia On-Demand — Starts lightweight for coding, loads image/video/audio tools only when needed.

What You Can Do

  • Code generation and implementation
  • Bug debugging and fixing
  • Code refactoring and optimization
  • Codebase exploration and documentation
  • Terminal operations (build, test, deploy)
  • Multi-file changes across a project
  • Development workflow automation

Requirements

  • CellCog Desktop must be installed and connected (see cowork-cog for setup)
  • Chat mode: "agent core" (lightweight, coding-optimized)
  • Co-work enabled: enable_cowork=True with cowork_working_directory

Related Skills

  • cowork-cog — Setup guide for CellCog Desktop
  • project-cog — Knowledge workspaces for project context

Statistics

Downloads 63
Stars 0
Current installs 1
All-time installs 1
Versions 4
Comments 0
Created Mar 31, 2026
Updated Apr 6, 2026

Latest Changes

v1.0.3 · Apr 6, 2026

- Improved and clarified skill description to emphasize direct machine access and suitability for agent workflows. - Updated prerequisites and quick start guides with references to the Cowork-Cog skill for CellCog Desktop setup. - Simplified and reorganized documentation for easier readability, focusing on core capabilities, requirements, and workflow. - Consolidated explanation of features, removing repetitive detail and focusing on key functions such as code generation, debugging, and terminal operations. - Added a "Related Skills" section to cross-link relevant CellCog skills. - No code or interface changes; documentation update only.

Quick Install

clawhub install code-cog
EU Made in Europe

Chat with 100+ AI Models in one App.

Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.