/coding-agent
Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple
$ npx -y skills add swarmclawai/swarmclaw --skill coding-agent --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition โ
- You can call itInvoke it directly when you want it.
- Slash command
/coding-agent
Context preview
The summary Claude sees to decide when to auto-load this skill.
Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple
SKILL.md
coding-agent.SKILL.mdname: coding-agent
description: 'Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly), reading code (use read/file tools), or work inside the SwarmClaw workspace itself.'
metadata:
{
"openclaw": { "emoji": "๐งฉ", "requires": { "anyBins": ["claude", "codex", "opencode", "pi"] } },
}Coding Agent
Delegate coding tasks to external coding agents via shell tools.
Agent Execution Modes
Claude Code (recommended)
Use `--print --permission-mode bypassPermissions` for non-interactive execution:
cd /path/to/project && claude --permission-mode bypassPermissions --print 'Your task here'
For background execution, use the shell tool's background mode.
**Do NOT use PTY mode with Claude Code** โ `--print` mode keeps full tool access and avoids interactive confirmation dialogs.
Codex
Codex requires a git repository and PTY mode:
# Quick one-shot (auto-approves changes)
cd /path/to/project && codex exec --full-auto 'Build a dark mode toggle'
# Codex refuses to run outside a git directory. For scratch work:
SCRATCH=$(mktemp -d) && cd $SCRATCH && git init && codex exec "Your prompt"
Pi Coding Agent
# Install: npm install -g @mariozechner/pi-coding-agent
cd /path/to/project && pi 'Your task'
# Non-interactive mode
pi -p 'Summarize src/'
# Different provider/model
pi --provider openai --model gpt-4o-mini -p 'Your task'
OpenCode
cd /path/to/project && opencode run 'Your task'
PR Reviews
Clone to a temp folder or use git worktree โ never review PRs in the SwarmClaw project directory:
# Clone to temp for safe review
REVIEW_DIR=$(mktemp -d)
git clone https://github.com/user/repo.git $REVIEW_DIR
cd $REVIEW_DIR && gh pr checkout 130
codex review --base origin/main
# Or use git worktree
git worktree add /tmp/pr-130-review pr-130-branch
cd /tmp/pr-130-review && codex review --base main
Parallel Issue Fixing
Use git worktrees to fix multiple issues in parallel:
# Create worktrees
git worktree add -b fix/issue-78 /tmp/issue-78 main
git worktree add -b fix/issue-99 /tmp/issue-99 main
# Launch agents (use background shell execution)
cd /tmp/issue-78 && codex --yolo 'Fix issue #78: <description>. Commit when done.'
cd /tmp/issue-99 && codex --yolo 'Fix issue #99: <description>. Commit when done.'
# Create PRs after
cd /tmp/issue-78 && git push -u origin fix/issue-78
gh pr create --repo user/repo --head fix/issue-78 --title "fix: ..." --body "..."
# Cleanup
git worktree remove /tmp/issue-78
git worktree remove /tmp/issue-99
Rules
1. **Use the right execution mode per agent**: Claude Code uses `--print` (no PTY); Codex/Pi/OpenCode may need interactive terminal. 2. **Respect tool choice** โ if the user asks for Codex, use Codex. Don't silently switch agents. 3. **Be patient** โ don't kill sessions because they seem slow. 4. **Monitor progress** โ check output periodically without interfering. 5. **Never run coding agents inside the SwarmClaw project directory** โ use a separate project directory or temp folder.
Progress Updates
When spawning coding agents in the background:
- Send a short message when you start (what's running, where).
- Update only when something changes (milestone, error, completion).
- If you kill a session, say so immediately and explain why.
Read more
name: coding-agent
description: 'Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly), reading code (use read/file tools), or work inside the SwarmClaw workspace itself.'
metadata:
{
"openclaw": { "emoji": "๐งฉ", "requires": { "anyBins": ["claude", "codex", "opencode", "pi"] } },
}Coding Agent
Delegate coding tasks to external coding agents via shell tools.
Agent Execution Modes
Claude Code (recommended)
Use `--print --permission-mode bypassPermissions` for non-interactive execution:
cd /path/to/project && claude --permission-mode bypassPermissions --print 'Your task here'
For background execution, use the shell tool's background mode.
**Do NOT use PTY mode with Claude Code** โ `--print` mode keeps full tool access and avoids interactive confirmation dialogs.
Codex
Codex requires a git repository and PTY mode:
# Quick one-shot (auto-approves changes) cd /path/to/project && codex exec --full-auto 'Build a dark mode toggle' # Codex refuses to run outside a git directory. For scratch work: SCRATCH=$(mktemp -d) && cd $SCRATCH && git init && codex exec "Your prompt"
Pi Coding Agent
# Install: npm install -g @mariozechner/pi-coding-agent cd /path/to/project && pi 'Your task' # Non-interactive mode pi -p 'Summarize src/' # Different provider/model pi --provider openai --model gpt-4o-mini -p 'Your task'
OpenCode
cd /path/to/project && opencode run 'Your task'
PR Reviews
Clone to a temp folder or use git worktree โ never review PRs in the SwarmClaw project directory:
# Clone to temp for safe review REVIEW_DIR=$(mktemp -d) git clone https://github.com/user/repo.git $REVIEW_DIR cd $REVIEW_DIR && gh pr checkout 130 codex review --base origin/main # Or use git worktree git worktree add /tmp/pr-130-review pr-130-branch cd /tmp/pr-130-review && codex review --base main
Parallel Issue Fixing
Use git worktrees to fix multiple issues in parallel:
# Create worktrees git worktree add -b fix/issue-78 /tmp/issue-78 main git worktree add -b fix/issue-99 /tmp/issue-99 main # Launch agents (use background shell execution) cd /tmp/issue-78 && codex --yolo 'Fix issue #78: <description>. Commit when done.' cd /tmp/issue-99 && codex --yolo 'Fix issue #99: <description>. Commit when done.' # Create PRs after cd /tmp/issue-78 && git push -u origin fix/issue-78 gh pr create --repo user/repo --head fix/issue-78 --title "fix: ..." --body "..." # Cleanup git worktree remove /tmp/issue-78 git worktree remove /tmp/issue-99
Rules
1. **Use the right execution mode per agent**: Claude Code uses `--print` (no PTY); Codex/Pi/OpenCode may need interactive terminal. 2. **Respect tool choice** โ if the user asks for Codex, use Codex. Don't silently switch agents. 3. **Be patient** โ don't kill sessions because they seem slow. 4. **Monitor progress** โ check output periodically without interfering. 5. **Never run coding agents inside the SwarmClaw project directory** โ use a separate project directory or temp folder.
Progress Updates
When spawning coding agents in the background:
- Send a short message when you start (what's running, where).
- Update only when something changes (milestone, error, completion).
- If you kill a session, say so immediately and explain why.
The self-hosted AI agent runtime and multi-agent framework for autonomous agents. Open-source agent swarms with durable agent memory, MCP tools, skills, delegation, schedules, and 23+ LLM providers โ a practical Claude Code and LangChain alternative.
Repo: swarmclawai/swarmclaw
Other skills on swarmclaw.
- /github
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: local git operations (use git directly), non-GitHub
Open skill - /google-workspace
Use Google Workspace CLI (`gws`) for Drive, Docs, Sheets, Gmail, Calendar, Chat, and related Workspace API tasks.
Open skill - /nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when asked to create, generate, or edit images and a Gemini API key is available. Supports text-to-image generation, single-image editing, and multi-image composition (up to 14 images).
Open skill - /nano-pdf
Edit or create PDFs with natural-language instructions using the nano-pdf CLI. Use when asked to make a PDF, edit a PDF, add pages, change text in a PDF, or convert content to PDF format.
Open skill - /openai-image-gen
Generate images via OpenAI Images API (GPT Image, DALL-E 3, DALL-E 2). Supports batch generation with random prompt sampler and HTML gallery output. Use when asked to generate images with OpenAI and an OPENAI_API_KEY is available.
Open skill - /resourceful-problem-solving
Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to any request where the agent lacks a dedicated tool.
Open skill

