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 (sp...

Security Scan

The instructions match the stated goal (delegating coding work to Codex/Claude/Pi) but the SKILL.md explicitly instructs users to disable sandboxing/permission checks and to run long-lived background agents with filesystem access — practices that increase risk and are not properly scoped or justified.

Purpose & Capability

The required binaries (claude, codex, opencode, pi) and the bash-first background/PTY approach align with the skill's stated purpose of delegating coding tasks. However, the document repeatedly recommends flags that disable safety (e.g., --yolo, --permission-mode bypassPermissions, --dangerously-skip-permissions), which are related to the tooling but are excessive for ordinary coding tasks and remove protective controls.

Instruction Scope

The instructions tell the agent to create temp repos, clone arbitrary GitHub repos, change into arbitrary working directories, run long-running background sessions, and interact with those sessions (write/paste/send-keys), which gives broad filesystem and network reach. Crucially, the guide explicitly instructs bypassing permission/sandbox checks for some CLIs; that is scope-creep toward disabling safety protections and could enable unintended data access/exfiltration.

Install Mechanism

This is an instruction-only skill with no install spec and no code files, so it does not write code or binaries to disk during install — lowest install risk.

Credentials

The skill declares no required environment variables or credentials, which is appropriate. However the instructions reference local config (e.g., ~/.codex/config.toml) and use of git/gh CLIs (which may implicitly use GitHub credentials) without declaring them. That mismatch means the agent may rely on unstated credentials/config already on the host.

Persistence & Privilege

The skill is not marked always:true and does not request modifying other skills or system-wide settings. It does, however, instruct use of background sessions and mentions an 'elevated' option for running on host instead of sandbox; these are potentially powerful but are part of the runtime tool rather than the skill manifest itself.

What to consider before installing

This skill appears to be what it claims (a helper to spawn coding agents), but it contains explicit recommendations to bypass sandboxing and permission checks and to run background agents with filesystem access. Before installing or using it: - Avoid using flags like --yolo, --permission-mode bypassPermissions, or --dangerously-skip-permissions unless you fully understand and accept the risk. They disable safety controls. - Run these agents in an isolated environment (throwaway VM, container, or dedicated sandbox) and never in your home directory or repositories with secrets. - Verify any CLIs (codex/claude/opencode/pi) are legitimate official binaries and understand what credentials they use. Check ~/.codex/config.toml and your GitHub/GH CLI tokens; limit token scopes. - Prefer creating temporary clones/worktrees for reviews and wipe them after use; avoid granting host-level (elevated) execution unless necessary. - If you lack experience with sandboxing and process isolation, treat this skill as high-risk and consider manual workflows or safer tooling instead.

Coding Agent (bash-first)

Use bash (with optional background mode) for all coding agent work. Simple and effective.

⚠️ PTY Mode: Codex/Pi/OpenCode yes, Claude Code no

For Codex, Pi, and OpenCode, PTY is still required (interactive terminal apps):

# ✅ Correct for Codex/Pi/OpenCode
bash pty:true command:"codex exec 'Your prompt'"

For Claude Code (claude CLI), use --print --permission-mode bypassPermissions instead. --dangerously-skip-permissions with PTY can exit after the confirmation dialog. --print mode keeps full tool access and avoids interactive confirmation:

# ✅ Correct for Claude Code (no PTY needed)
cd /path/to/project && claude --permission-mode bypassPermissions --print 'Your task'

# For background execution: use background:true on the exec tool

# ❌ Wrong for Claude Code
bash pty:true command:"claude --dangerously-skip-permissions 'task'"

Bash Tool Parameters

Parameter	Type	Description
command	string	The shell command to run
pty	boolean	Use for coding agents! Allocates a pseudo-terminal for interactive CLIs
workdir	string	Working directory (agent sees only this folder's context)
background	boolean	Run in background, returns sessionId for monitoring
timeout	number	Timeout in seconds (kills process on expiry)
elevated	boolean	Run on host instead of sandbox (if allowed)

Process Tool Actions (for background sessions)

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

---

Quick Start: One-Shot Tasks

For quick prompts/chats, create a temp git repo and run:

# Quick chat (Codex needs a git repo!)
SCRATCH=$(mktemp -d) && cd $SCRATCH && git init && codex exec "Your prompt here"

# Or in a real project - with PTY!
bash pty:true workdir:~/Projects/myproject command:"codex exec 'Add error handling to the API calls'"

Why git init? Codex refuses to run outside a trusted git directory. Creating a temp repo solves this for scratch work.

---

The Pattern: workdir + background + pty

For longer tasks, use background mode with PTY:

# Start agent in target directory (with PTY!)
bash pty:true workdir:~/project background:true command:"codex exec --full-auto 'Build a snake game'"
# Returns sessionId for tracking

# Monitor progress
process action:log sessionId:XXX

# Check if done
process action:poll sessionId:XXX

# Send input (if agent asks a question)
process action:write sessionId:XXX data:"y"

# Submit with Enter (like typing "yes" and pressing Enter)
process action:submit sessionId:XXX data:"yes"

# Kill if needed
process action:kill sessionId:XXX

Why workdir matters: Agent wakes up in a focused directory, doesn't wander off reading unrelated files (like your soul.md 😅).

---

Codex CLI

Model: gpt-5.2-codex is the default (set in ~/.codex/config.toml)

Flags

Flag	Effect
exec "prompt"	One-shot execution, exits when done
--full-auto	Sandboxed but auto-approves in workspace
--yolo	NO sandbox, NO approvals (fastest, most dangerous)

Building/Creating

# Quick one-shot (auto-approves) - remember PTY!
bash pty:true workdir:~/project command:"codex exec --full-auto 'Build a dark mode toggle'"

# Background for longer work
bash pty:true workdir:~/project background:true command:"codex --yolo 'Refactor the auth module'"

Reviewing PRs

⚠️ CRITICAL: Never review PRs in OpenClaw's own project folder! Clone to temp folder or use git worktree.

# Clone to temp for safe review
REVIEW_DIR=$(mktemp -d)
git clone https://github.com/user/repo.git $REVIEW_DIR
cd $REVIEW_DIR && gh pr checkout 130
bash pty:true workdir:$REVIEW_DIR command:"codex review --base origin/main"
# Clean up after: trash $REVIEW_DIR

# Or use git worktree (keeps main intact)
git worktree add /tmp/pr-130-review pr-130-branch
bash pty:true workdir:/tmp/pr-130-review command:"codex review --base main"

Batch PR Reviews (parallel army!)

# Fetch all PR refs first
git fetch origin '+refs/pull/*/head:refs/remotes/origin/pr/*'

# Deploy the army - one Codex per PR (all with PTY!)
bash pty:true workdir:~/project background:true command:"codex exec 'Review PR #86. git diff origin/main...origin/pr/86'"
bash pty:true workdir:~/project background:true command:"codex exec 'Review PR #87. git diff origin/main...origin/pr/87'"

# Monitor all
process action:list

# Post results to GitHub
gh pr comment <PR#> --body "<review content>"

---

Claude Code

# Foreground
bash workdir:~/project command:"claude --permission-mode bypassPermissions --print 'Your task'"

# Background
bash workdir:~/project background:true command:"claude --permission-mode bypassPermissions --print 'Your task'"

---

OpenCode

bash pty:true workdir:~/project command:"opencode run 'Your task'"

---

Pi Coding Agent

# Install: npm install -g @mariozechner/pi-coding-agent
bash pty:true workdir:~/project command:"pi 'Your task'"

# Non-interactive mode (PTY still recommended)
bash pty:true command:"pi -p 'Summarize src/'"

# Different provider/model
bash pty:true command:"pi --provider openai --model gpt-4o-mini -p 'Your task'"

Note: Pi now has Anthropic prompt caching enabled (PR #584, merged Jan 2026)!

---

Parallel Issue Fixing with git worktrees

For fixing multiple issues in parallel, use git worktrees:

# 1. Create worktrees for each issue
git worktree add -b fix/issue-78 /tmp/issue-78 main
git worktree add -b fix/issue-99 /tmp/issue-99 main

# 2. Launch Codex in each (background + PTY!)
bash pty:true workdir:/tmp/issue-78 background:true command:"pnpm install && codex --yolo 'Fix issue #78: <description>. Commit and push.'"
bash pty:true workdir:/tmp/issue-99 background:true command:"pnpm install && codex --yolo 'Fix issue #99 from the approved ticket summary. Implement only the in-scope edits and commit after review.'"

# 3. Monitor progress
process action:list
process action:log sessionId:XXX

# 4. Create PRs after fixes
cd /tmp/issue-78 && git push -u origin fix/issue-78
gh pr create --repo user/repo --head fix/issue-78 --title "fix: ..." --body "..."

# 5. Cleanup
git worktree remove /tmp/issue-78
git worktree remove /tmp/issue-99

---

⚠️ Rules

1. Use the right execution mode per agent:
   • Codex/Pi/OpenCode: pty:true
   • Claude Code: --print --permission-mode bypassPermissions (no PTY required)
2. 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.
3. Be patient - don't kill sessions because they're "slow"
4. Monitor with process:log - check progress without interfering
5. --full-auto for building - auto-approves changes
6. vanilla for reviewing - no special flags needed
7. Parallel is OK - run many Codex processes at once for batch work
8. NEVER start Codex in ~/.openclaw/ - it'll read your soul docs and get weird ideas about the org chart!
9. NEVER checkout branches in ~/Projects/openclaw/ - that's the LIVE OpenClaw instance!

---

Progress Updates (Critical)

When you spawn coding agents in the background, keep the user in the loop.

• Send 1 short message when you start (what's running + where).
• Then only update again when something changes:
  • a milestone completes (build finished, tests passed)
  • the agent asks a question / needs input
  • you hit an error or need user action
  • the agent finishes (include what changed + where)
• If you kill a session, immediately say you killed it and why.

This prevents the user from seeing only "Agent failed before reply" and having no idea what happened.

---

Auto-Notify on Completion

For long-running background tasks, append a wake trigger to your prompt so OpenClaw gets notified immediately when the agent finishes (instead of waiting for the next heartbeat):

... your task here.

When completely finished, run this command to notify me:
openclaw system event --text "Done: [brief summary of what was built]" --mode now

Example:

bash pty:true workdir:~/project background:true command:"codex --yolo exec 'Build a REST API for todos.

When completely finished, run: openclaw system event --text \"Done: Built todos REST API with CRUD endpoints\" --mode now'"

This triggers an immediate wake event — Skippy gets pinged in seconds, not 10 minutes.

---

Learnings (Jan 2026)

• PTY is essential: Coding agents are interactive terminal apps. Without pty:true, output breaks or agent hangs.
• Git repo required: Codex won't run outside a git directory. Use mktemp -d && git init for scratch work.
• exec is your friend: codex exec "prompt" runs and exits cleanly - perfect for one-shots.
• submit vs write: Use submit to send input + Enter, write for raw data without newline.
• Sass works: Codex responds well to playful prompts. Asked it to write a haiku about being second fiddle to a space lobster, got: "Second chair, I code / Space lobster sets the tempo / Keys glow, I follow" 🦞