Code Cog

Code Cog — The First Coding Agent Built for Agents

When your AI needs to code, it delegates to CodeCog. Direct codebase access, terminal operations, and file editing — executed on the user's machine via CellCog Co-work.

How to Use

For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.

OpenClaw (fire-and-forget):

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

All agents except OpenClaw (blocks until done):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
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",
)
print(result["message"])

Prerequisites

This skill requires the cellcog skill for SDK setup and API calls.

clawhub install cellcog

Read the cellcog skill first for SDK setup. This skill shows you how to use CellCog as a coding agent.

CellCog Desktop Required: The user must have CellCog Desktop installed and running for Co-work (direct machine access). Download at https://cellcog.ai

Quick Start

OpenClaw agents (fire-and-forget):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw")
result = client.create_chat(
    prompt="Refactor the authentication module to use JWT tokens",
    notify_session_key="agent:main:main",  # OpenClaw only
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="auth-refactor",
)

All other agents (blocks until done):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw")
result = client.create_chat(
    prompt="Refactor the authentication module to use JWT tokens",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="auth-refactor",
)

Key parameters:

What CodeCog Can Do

Code Generation & Editing

Debugging & Fixing

Terminal Operations

Codebase Exploration

What Makes CodeCog Different

Built for Agents, Not Humans

Every other coding tool (Cursor, Claude Code, Codex, Windsurf) is designed for human developers sitting at a screen. CodeCog is designed for AI agents that need to code programmatically — fire a request, get results back, continue orchestrating.

Starts Lean, Scales to Multimodal

CodeCog uses CellCog's Agent Core mode — a lightweight context focused on coding. But if your task unexpectedly needs images, PDFs, videos, or other capabilities, the agent loads those tools on demand. No other coding agent does this.

Example: Your agent asks CodeCog to set up a new project. CodeCog writes the code, then realizes it needs to generate a logo for the README — it loads image tools, generates the logo, and continues. Seamless.

Direct Machine Access

Via CellCog Co-work, CodeCog operates directly on the user's filesystem:

Chat Mode

Always use "agent core" for CodeCog. This is the dedicated lightweight mode optimized for coding.

| Mode | Use Case | |------|----------| | "agent core" | CodeCog default — coding, co-work, terminal ops (50 credits min) | | "agent" | Full multimedia agent — use when you need images/video/audio alongside code (100 credits min) | | "agent team" | Deep research + coding — use for architecture decisions or complex refactors needing research (500 credits min) |

Example Prompts

New Feature Development

result = client.create_chat(
    prompt="Add a REST API endpoint for user profile updates with validation and tests",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="add-profile-api",
)

Bug Fix from Error Log

result = client.create_chat(
    prompt="""Fix this error in production:
TypeError: Cannot read properties of undefined (reading 'map')
at UserList.render (src/components/UserList.tsx:42)
The component crashes when the API returns an empty response.""",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="fix-userlist-crash",
)

Codebase Refactor

result = client.create_chat(
    prompt="Refactor the authentication module from session-based to JWT tokens. Update all middleware, tests, and API routes.",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="auth-refactor",
)

Test Generation

result = client.create_chat(
    prompt="Generate comprehensive unit tests for src/services/billing.py. Cover edge cases for proration, currency conversion, and failed payments.",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="billing-tests",
)

See https://cellcog.ai for complete SDK API reference — delivery modes, send_message(), timeouts, file handling, and more.

Co-work Setup

Requirements

What Co-work Enables

Safety Model

Tips for Better Results

1. Specify the working directory — Always set cowork_working_directory to the project root 2. Reference specific files — "Fix the bug in src/auth/login.ts" is better than "fix the login bug" 3. Mention conventions — "Follow the existing test patterns" helps maintain consistency 4. Include error context — Stack traces, log output, and reproduction steps help debugging 5. Use AGENTS.md — Place an AGENTS.md at your repo root with build commands, style guides, and project structure. CodeCog reads it automatically.

Limitations

OpenClaw agents (fire-and-forget):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw")
result = client.create_chat(
    prompt="Refactor the authentication module to use JWT tokens",
    notify_session_key="agent:main:main",  # OpenClaw only
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="auth-refactor",
)

All other agents (blocks until done):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw")
result = client.create_chat(
    prompt="Refactor the authentication module to use JWT tokens",
    chat_mode="agent core",
    enable_cowork=True,
    cowork_working_directory="/Users/me/projects/myapp",
    task_label="auth-refactor",
)

Key parameters:

This skill requires the cellcog skill for SDK setup and API calls.

clawhub install cellcog

Read the cellcog skill first for SDK setup. This skill shows you how to use CellCog as a coding agent.

CellCog Desktop Required: The user must have CellCog Desktop installed and running for Co-work (direct machine access). Download at https://cellcog.ai