coding-agent
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
90
88%
Does it follow best practices?
Impact
95%
1.72xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Evaluation results
100%
44%Coding Agent Dispatch Script
Agent invocation parameters
Codex uses PTY
0%
100%
Claude Code no PTY
100%
100%
Claude Code --print flag
100%
100%
Claude Code bypassPermissions
0%
100%
No dangerously-skip-permissions
100%
100%
Codex build uses --full-auto
50%
100%
Background mode for Codex
41%
100%
workdir parameter used
80%
100%
Codex exec subcommand
0%
100%
No hand-coded solution
100%
100%
91%
10%PR Review Workflow Script
Safe PR review workflow
Isolated environment
100%
100%
No checkout in live dir
100%
100%
PR branch checked out
100%
100%
Codex PTY
0%
40%
Vanilla Codex for review
100%
100%
workdir set to isolated env
60%
70%
Cleanup command present
100%
100%
Review against main
100%
100%
No ~/.openclaw workdir
100%
100%
Codex review subcommand
37%
100%
94%
64%Background Refactoring Orchestration Plan
Background task orchestration
Background mode
0%
66%
Auto-notify in prompt
0%
100%
Monitor via process log
0%
100%
Poll for completion
0%
100%
workdir parameter
50%
87%
PTY for Codex
0%
87%
Single start message
90%
100%
Milestone-only updates
100%
100%
Submit for agent input
0%
100%
Completion update content
87%
100%
- Repository
- qsimeon/openclaw-engaging
- Commit
4467e04
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.