coding-agent

Orchestrate interactive coding agents in PTY-backed sessions for development tasks.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/Yogi-076/Vajrascan.on --skill coding-agent-yogi-076
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/Yogi-076/Vajrascan.on/tree/main/moltbot/skills/coding-agent
Command: npx skills add https://github.com/Yogi-076/Vajrascan.on --skill coding-agent-yogi-076

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides reliable, repeatable guidance for running interactive coding agents (Codex, Claude Code, OpenCode, Pi) in terminal environments so they do not hang, lose formatting, or read unintended files during programmatic workflows.

Core Features & Use Cases

  • PTY-first execution: Emphasizes allocating a pseudo-terminal (pty:true) so interactive CLIs render correctly and remain responsive.
  • Background session orchestration: Start agents in background mode, receive a sessionId, and use process actions to list, poll, retrieve logs, send input, and kill sessions.
  • Safe workspace handling: Use workdir and temporary git repos or worktrees for reviews and batch PR fixes to avoid editing live Moltbot or sensitive directories.
  • Notification and monitoring: Attach wake triggers so Moltbot is notified on completion and follow the progress update rules to keep users informed.

Quick Start

Start a background Codex agent in the project workdir with pty:true and monitor its logs until it reports completion.

Frequently Asked Questions about coding-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Claude Code in a background terminal session without it hanging?

You allocate a pseudo-terminal with pty:true to run Claude Code in a PTY-backed background session. This prevents the interactive CLI from hanging or losing formatting during programmatic workflows and long-running automation tasks.

What is the best way to orchestrate Codex agents for batch PR fixes?

The best way to orchestrate Codex for batch PR fixes is using a background session manager that supports list, poll, log, and submit actions. Apply workdir and temporary git repos to safely review and fix PRs without editing live directories.

Do I need a git-initialized workdir to run Codex agents?

Yes, you need a git-initialized or targeted workdir to run Codex agents. Safe workspace handling uses temporary git repos or worktrees for reviews and batch PR fixes to avoid editing sensitive directories.

How do I monitor a long-running coding agent in a background process?

You monitor a long-running background coding agent by polling its logs using the sessionId. Start the agent in background mode, then use list, poll, and log actions to retrieve output and track progress until it reports completion.

Why does my interactive coding CLI lose formatting when automated?

Interactive coding CLIs lose formatting when automated without a pseudo-terminal because the TUI rendering expects a terminal interface. Allocating a PTY with pty:true ensures the interactive agent renders correctly and remains responsive.

Can I use OpenCode and Pi agents for automated code review?

Yes, OpenCode and Pi agents can be used for automated code review. Start them in PTY-backed background sessions and use safe workdir handling with temporary git repos to review code without editing live directories.