mcpField
C
coding-agent

coding-agent

github.com/cowork-osAgent workflows51762 installsUpdated today
Repository

About coding-agent

coding-agent is a skill for programmatic control of Codex CLI, Claude Code, OpenCode, or Pi Coding Agent through background processes. It is intended for tasks that can be handled through this automated execution.

Key features

  1. 01Run Codex CLI in the background
  2. 02Run Claude Code in the background
  3. 03Run OpenCode in the background
  4. 04Run Pi Coding Agent in the background
  5. 05Control coding agents programmatically

Use cases

  1. 01Automate a coding task with Codex CLI
  2. 02Run Claude Code as a background process
  3. 03Control OpenCode or Pi Coding Agent programmatically

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cowork-os/cowork-os --skill coding-agent

After installing, type/coding-agentin Claude Code to confirm it loaded.

Bundled filesreferences/full-guidance.mdscripts/.gitkeep

Details

From the project README

Coding-agent

Purpose

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Routing

  • Use when: Use when the user asks to run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
  • Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead. Avoid using in non-interactive environments unless automation can fully satisfy prompts.
  • Outputs: Outcome from Coding-agent: task-specific result plus concrete action notes.
  • Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.

Trigger Examples

Positive
  • Use the coding-agent skill for this request.
  • Help me with coding-agent.
  • Use when the user asks to run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
  • Coding-agent: provide an actionable result.
Negative
  • Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead. Avoid using in non-interactive environments unless automation can fully satisfy prompts.
  • Do not use coding-agent for unrelated requests.
  • This request is outside coding-agent scope.
  • This is conceptual discussion only; no tool workflow is needed.

Runtime Prompt

  • Current runtime prompt length: 982 characters.
  • Runtime prompt is defined directly in ../coding-agent.json.

Comments

Markdown supported