Agent-Skills.md

Agent Skills: 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.

UncategorizedID: steipete/clawdis/coding-agent

Repository

steipete/clawdis
openclawLicense: MIT
341,75467,475

Install this agent skill to your local

pnpm dlx add-skill https://github.com/openclaw/openclaw/tree/HEAD/skills/coding-agent

Skill Files

Browse the full folder contents for coding-agent.

Download Skill

Loading file tree…

skills/coding-agent/SKILL.md

Skill Metadata

Name
coding-agent
Description
"Delegate coding work to Codex, Claude Code, OpenCode, or Pi as background workers; not simple edits or read-only code lookup."

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

Append this shape to every worker prompt with real values:

Notification route:
- channel: <notifyChannel>
- target: <notifyTarget>
- account: <notifyAccount or omit>
- reply_to: <notifyReplyTo or omit>
- thread_id: <notifyThreadId or omit>

When finished, send exactly one completion or failure message using:
openclaw message send --channel <channel> --target '<target>' --message '<brief result>'
Add --account, --reply-to, or --thread-id only when present above.
Do not use openclaw system event or heartbeat.

If no trustworthy route exists, say completion auto-notify is unavailable.

Launch forms

Write the worker prompt to a temp file first. This avoids shell quoting bugs when the required notification block contains quotes or newlines.

PROMPT=$(mktemp -t openclaw-worker-prompt.XXXXXX)
cat >"$PROMPT" <<'EOF'
Task.
<notification block>
EOF
printf 'prompt file: %s\n' "$PROMPT"

Use $PROMPT when launching from the same shell/session. If using a separate tool call, substitute the printed path.

Codex:

bash pty:true background:true workdir:/path/repo command:"codex exec - < \"$PROMPT\""

Claude Code:

bash background:true workdir:/path/repo command:"claude --permission-mode bypassPermissions --print < \"$PROMPT\""

OpenCode:

bash pty:true background:true workdir:/path/repo command:"opencode run < \"$PROMPT\""

Pi:

bash pty:true background:true workdir:/path/repo command:"pi -p \"$(cat \"$PROMPT\")\""

Long issue-to-PR work

  1. Create/reuse a GitHub issue as durable spec.
  2. Include issue URL, repo, base branch, expected PR, proof, and notification route.
  3. Tell worker to branch, implement, test, run review until no accepted actionable findings, open PR.
  4. Return issue URL and sessionId immediately.
  5. Monitor with process; cancel through Task Registry if mirrored there.

Scratch Codex

Codex needs a trusted git repo:

SCRATCH=$(mktemp -d)
git -C "$SCRATCH" init
PROMPT=$(mktemp -t openclaw-worker-prompt.XXXXXX)
cat >"$PROMPT" <<'EOF'
Build X.
<notification block>
EOF
printf 'prompt file: %s\n' "$PROMPT"
bash pty:true background:true workdir:$SCRATCH command:"codex exec - < \"$PROMPT\""

Process actions

  • list: running/recent sessions.
  • poll: status.
  • log: output.
  • submit: send input + Enter.
  • write: raw stdin.
  • paste: paste text.
  • kill: terminate.

Status to user

  • Say what started, where, and sessionId.
  • Update only on milestone, worker question, error, user action needed, or finish.
  • If killed, say why.