Lucky 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 skill's instructions largely match a coding-agent purpose, but there are notable mismatches between its declared requirements and what the runtime instructions expect, plus it documents dangerous runtime options (no-sandbox / elevated) that increase risk — review before use.

Purpose & Capability

The name/description (delegating coding tasks to Codex/Claude/Pi) matches the SKILL.md instructions: it tells the agent how to spawn background coding agents, use PTY, and operate in workdirs. However, the registry metadata omits several runtime dependencies the instructions clearly rely on (bash with PTY support, git, gh, and a 'process' background/session tool). Requiring codex/claude/opencode/pi is expected, but omission of bash/git/gh/process is an inconsistency.

Instruction Scope

SKILL.md directs creating temporary git repos, cloning remote repos, running many background agents (batch PR reviews), and references local config (~/.codex/config.toml). It also prescribes using '--yolo' (no sandbox/no approvals) and an 'elevated' option to run on host instead of sandbox. These behaviors go beyond simple one-shot edits and include actions that can read/modify many files and run agents without sandboxing; the instructions also assume availability of tools not declared in metadata.

Install Mechanism

Instruction-only skill with no install spec — low install-time risk. Nothing will be written to disk at install time by the skill bundle itself.

Credentials

The skill declares no required env vars or config paths, yet the instructions implicitly rely on user-side config (~/.codex/config.toml), GitHub tooling (gh), and local git identity/credentials for cloning and PR checkout. The skill does not declare these requirements or request the necessary credentials, which is an inconsistency and could lead to unclear credential usage at runtime. Also the guidance to use '--yolo' or 'elevated' bypasses sandbox/approval controls — these are powerful capabilities that are not constrained or explained further.

Persistence & Privilege

The skill is not force-enabled (always:false) and follows the platform default for autonomous invocation; it does not request persistent installation or modify other skills. However, its runtime instructions encourage spawning multiple background sessions which increase blast radius at runtime — this is a usage risk rather than an install-time privilege escalation.

What to consider before installing

This skill appears to be what it says — a guide for running background coding agents — but there are a few red flags you should consider before installing or using it: - The SKILL.md expects tools and config that the registry metadata does not declare: ensure you have a bash tool that supports pty:true, git, and GitHub CLI (gh) available and understand how they will be used. - The instructions document dangerous runtime modes: '--yolo' (no sandbox/no approvals) and an 'elevated' host mode. Do not use these unless you fully trust the agent and understand the security implications (they allow agents to run with fewer restrictions and can modify your system or repositories). - The skill references local config (~/.codex/config.toml) and will operate on workdirs (cloning repos, batch-processing PRs). Confirm you are comfortable with the agent having access to the target folders and any credentials that your git/gh setup provides. - Because the metadata omits some runtime needs, ask the publisher (or inspect the skill) for a clear list of required binaries and any expected credential usage. If you plan to run it at scale (batch PR reviews), test first in isolated temp directories and avoid using the 'no sandbox' or 'elevated' options. If you want me to, I can extract more specific lines from SKILL.md that reference risky flags and missing dependencies, or produce a suggested minimal safe policy for running this skill (e.g., wrapper that forbids '--yolo' and 'elevated').

Coding Agent (bash-first)

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

⚠️ PTY Mode Required!

Coding agents (Codex, Claude Code, Pi) are interactive terminal applications that need a pseudo-terminal (PTY) to work correctly. Without PTY, you'll get broken output, missing colors, or the agent may hang.

Always use pty:true when running coding agents:

# ✅ Correct - with PTY
bash pty:true command:"codex exec 'Your prompt'"

# ❌ Wrong - no PTY, agent may break
bash command:"codex exec 'Your prompt'"

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

# With PTY for proper terminal output
bash pty:true workdir:~/project command:"claude 'Your task'"

# Background
bash pty:true workdir:~/project background:true command:"claude '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. Always use pty:true - coding agents need a terminal!
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" 🦞