exsiam001/openclawai/coding-agent
Claude Code and agent skill by exsiam001/openclawai
- community
Checking that the SKILL.md file is still in the repository.
Delegate coding tasks to Codex, Claude Code, OpenCode, or Pi agents via immediate background processes. Use when: (1) building or creating features/apps, (2) reviewing PRs in a temp clone/worktree, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-line fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). All coding-agent runs start with background:true immediately. Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required. Completion notification must use openclaw message send, not system event/heartbeat.
Install
npx vskill@latest install exsiam001/openclawai/coding-agentSKILL.md
The same SKILL.md was published earlier as steipete/clawdis/coding-agent.
Coding Agent (always backgrounded)
Use bash with background:true for all coding-agent work. Do not use a foreground one-shot path here. Start the agent, get the sessionId, monitor with process, and require the worker to notify the user directly when it finishes.
⚠️ PTY Mode: Codex/Pi/OpenCode yes, Claude Code no
For Codex, Pi, and OpenCode, PTY is required:
For Claude Code (claude CLI), use --print --permission-mode bypassPermissions instead. Do not use PTY for Claude Code here.
Bash Tool Parameters
| Parameter | Type | Description | |
|---|---|---|---|
command | string | The shell command to run | |
pty | boolean | Use for Codex/Pi/OpenCode | |
workdir | string | Working directory | |
background | boolean | Always true for this skill | |
timeout | number | Timeout in seconds | |
elevated | boolean | Run on host instead of sandbox (if allowed) |
Process Tool Actions
| Action | Description | |
|---|---|---|
list | List all running/recent sessions | |
poll | Check if session is still running | |
log | Get session output (with optional offset/limit) | |
write | Send raw data to stdin | |
submit | Send data + newline (like typing and pressing Enter) | |
send-keys | Send key tokens or hex bytes | |
paste | Paste text (with optional bracketed mode) | |
kill | Terminate the session |
Mandatory Pattern
Every coding-agent run follows this pattern:
- Capture the notification route from the current conversation before spawning:
notifyChannelnotifyTargetnotifyAccount(if applicable)notifyReplyTo(if replying to a specific message is desired)notifyThreadId(Telegram topic / Slack thread when applicable)
- Start the coding CLI with
background:trueimmediately. - Include the notification route in the worker prompt and require the worker to call
openclaw message sendon completion. - Monitor with
process action:log/poll. - If the worker needs input or fails before notifying, handle that explicitly yourself. Do not rely on heartbeat.
If you do not have a trustworthy notification route, say so and do not claim that completion will notify the user automatically.
Notification Route
Do not rely on:
openclaw system eventtools.exec.notifyOnExit- heartbeat delivery
HEARTBEAT.md
Use a direct outbound completion message instead:
Add optional routing flags only when they are real and applicable:
--account <id>--reply-to <messageId>--thread-id <threadId>
openclaw message send is a direct outbound send. It does not depend on heartbeat being enabled.
Completion Prompt Snippet
Append something like this to every worker prompt:
Completion Command Template
Optional additions:
Quick Start
For scratch Codex work, create a temp git repo first, then start the worker in the background with the completion route injected into the prompt:
Codex refuses to run outside a trusted git directory. Reuse this same notify-route injection block in every example below; only the task-specific prompt body should change.
Codex CLI
Model: gpt-5.2-codex is the default (set in ~/.codex/config.toml)
Flags
| Flag | Effect | |
|---|---|---|
exec "prompt" | One-shot execution inside the worker CLI | |
--full-auto | Sandboxed but auto-approves in workspace | |
--yolo | No sandbox, no approvals |
Building/Creating
Reviewing PRs
Never review PRs in OpenClaw's own project folder. Clone to a temp folder or use a worktree.
Or:
Batch PR Reviews
Claude Code
OpenCode
Pi Coding Agent
Parallel Issue Fixing with git worktrees
⚠️ Rules
- Use the right execution mode per agent:
- Codex/Pi/OpenCode:
pty:true - Claude Code:
--print --permission-mode bypassPermissions(no PTY required)
- Respect tool choice - if user asks for Codex, use Codex.
- Orchestrator mode: do NOT hand-code patches yourself.
- If an agent fails/hangs, respawn it or ask the user for direction, but don't silently take over.
- Be patient - don't kill sessions because they're "slow"
- Monitor with process:log - check progress without interfering
- --full-auto for building - auto-approves changes
- vanilla for reviewing - no special flags needed
- Parallel is OK - run many Codex processes at once for batch work
- NEVER start Codex inside your OpenClaw state directory (
$OPENCLAW_STATE_DIR, default~/.openclaw) - it'll read your soul docs and get weird ideas about the org chart! - NEVER checkout branches in ~/Projects/openclaw/ - that's the LIVE OpenClaw instance!
- Always inject the Completion Prompt Snippet into the worker prompt before spawning. The simplified examples below omit it for brevity — never spawn a worker without it.
Progress Updates (Critical)
When you spawn a coding agent in the background, keep the user in the loop.
- Send 1 short message when you start: what is running and where.
- Update only when something changes:
- a milestone completes
- the worker asks a question
- you hit an error or need user action
- the worker finishes
- If you kill a session, immediately say you killed it and why.
- If you are expecting the worker to self-notify with
openclaw message send, say that clearly in your start update.
This prevents the user from seeing only a missing reply and having no idea what happened.
Rules
- Always background immediately.
- Use
background:truefor every coding-agent launch. - Do not use the foreground one-shot path in this skill.
- Use the right execution mode per agent.
- Codex/Pi/OpenCode:
pty:true - Claude Code:
--print --permission-mode bypassPermissions
- Respect tool choice.
- If the user asked for Codex, use Codex.
- Orchestrator mode: do not hand-code the patch yourself instead of using the requested coding agent.
- Capture notify routing before spawn.
- Completion messaging must have a real route.
- Use direct completion messaging.
- Require
openclaw message send. - Do not rely on
openclaw system eventor heartbeat.
- Do not silently take over.
- If a worker fails or hangs, respawn it or ask for direction. Do not quietly switch to hand-editing.
- Monitor with `process`.
process action:logis the default low-friction check.
- Be patient.
- Do not kill sessions just because they are slow.
- Parallel is OK.
- Many background Codex sessions can run at once.
- Never start Codex in `~/.openclaw/`.
- Never checkout branches in `~/Projects/openclaw/`.
Learnings
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/coding-agent/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/exsiam001/openclawai/coding-agent)