coding-agent

SKILL.md

Delegate coding tasks to Codex, Claude Code, Pi, or OpenCode agents via background bash processes.

Supports four coding agents (Codex, Claude Code, Pi, OpenCode) with agent-specific execution modes: PTY required for Codex/Pi/OpenCode; Claude Code uses --print --permission-mode bypassPermissions without PTY

Background execution with session monitoring via process tool actions (log, poll, write, submit, kill) for long-running tasks

Designed for feature building, PR reviews, refactoring, and iterative coding with file exploration; includes patterns for parallel issue fixing using git worktrees

Requires git repository for Codex (use temp init for scratch work); respects workdir isolation to prevent unrelated file access

Coding Agent

Use for background feature builds, PR reviews, large refactors, and issue-to-PR loops. Do not use for simple edits, read-only lookup, ACP thread-bound work, or any run inside ~/.openclaw, $OPENCLAW_STATE_DIR, or active OpenClaw state dirs.

Hard rules

Always launch with background:true.

Codex, Pi, OpenCode: use pty:true.

Claude Code: no PTY; use claude --permission-mode bypassPermissions --print.

Capture a real notification route before spawning.

Worker must send completion/failure via openclaw message send.

Do not rely on heartbeat, system events, or notify-on-exit.

Monitor with process; do not kill slow workers without cause.

If user asked for a specific agent, use that agent.

If worker fails/hangs, respawn or ask; do not silently hand-code instead.

Never checkout branches or run background coding agents in ~/Projects/openclaw; use an isolated checkout.

Notification block