Coding Agent

What it does

When your agent uses it

• Creating new features
• Parallel coding with managed worktree isolation when subagents are available
• Refactoring large codebases
• Iterative coding that needs file exploration

Example prompts

• “/coding-agent”

Requirements

• Node.js

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

1. 1Always use tty:true - coding agents need a terminal.
2. 2Respect tool choice - if user asks for Codex, use Codex.
3. 3Be patient - don't kill sessions because they're "slow"
4. 4Monitor with process:log - check progress without interfering
5. 5full-auto for building - auto-approves changes
6. 6vanilla for reviewing - no special flags needed
7. 7Parallel is OK - run many Codex processes at once for batch work
8. 8NEVER start Codex in ~/.openclaw/ - it'll read your soul docs and get weird ideas about the org chart!
9. 9NEVER checkout branches in ~/Projects/openclaw/ - that's the LIVE OpenClaw instance!

What it can do on your machine

Read from SKILL.md and the folder at commit 9bb1c42. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git
  • codex
  • gh

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Coding Agent loads about 2.5k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 735 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~146

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from trpc-group/trpc-agent-go at commit 9bb1c42, republished under its Apache-2.0 licence (© trpc-group). 735 words, ~2,499 tokens.

name

coding-agent

description

Delegate coding tasks to Codex, Claude Code, or Pi agents via background host sessions. Use when: (1) building or creating new features or apps, (2) reviewing PRs or parallel coding with managed worktree isolation when subagents are available, (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, or any work in ~/clawd workspace (never spawn agents here). Requires OpenClaw host tools with exec_command plus write_stdin.

# ✅ Correct - with PTY
exec_command tty:true command:"codex exec 'Your prompt'"

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

# 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!
exec_command tty:true workdir:~/Projects/myproject command:"codex exec 'Add error handling to the API calls'"

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

# Monitor progress
write_stdin session_id:XXX chars:""

# Check if done
write_stdin session_id:XXX chars:""

# Send input (if agent asks a question)
write_stdin session_id:XXX chars:"y"

# Submit with Enter (like typing "yes" and pressing Enter)
write_stdin session_id:XXX chars:"yes" append_newline:true

# Kill if needed
kill_session session_id:XXX

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

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

{
  "task": "Review PR #130 against main. Inspect the diff, run focused checks, and report only actionable findings.",
  "isolation": "worktree",
  "timeout_seconds": 1800
}

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

{
  "task": "Review PR #86 against main. Inspect the diff, run focused checks, and report only actionable findings.",
  "isolation": "worktree",
  "timeout_seconds": 1800
}

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

# Background
exec_command tty:true workdir:~/project background:true command:"claude 'Your task'"

exec_command tty:true workdir:~/project command:"opencode run 'Your task'"

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

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

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

{
  "task": "Fix issue #78 from the approved ticket summary. Keep the scope tight, run focused tests, and report changed files plus verification.",
  "isolation": "worktree",
  "timeout_seconds": 3600
}

... 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

exec_command tty: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'"

© trpc-group, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in openclaw/skills/coding-agent of trpc-group/trpc-agent-go.

Open the folder on GitHubat commit 9bb1c42