Menu
Use when another workflow must launch Claude, Codex, or Gemini as a separate background sub-agent without opening a terminal. Spawns the `launchpad` agent with fenced JSON input and `run_in_background: true`.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Set up a repo-local just task runner with a root Justfile, optional .just/ helper scripts, and curated help, build, fmt, lint, test, and ci recipes. Use when a repo needs just, a Justfile, .just helpers, or when the user mentions task automation, "just build", "just lint", "just fmt", or dropping in a just system.
Create or harden CLIs intended primarily for AI or system consumption and secondarily for humans. Use when designing or implementing a JSON-first CLI with an MCP-ready contract seam, where every command supports machine output, errors are typed and actionable, mutating commands are auditable via corresponding read commands, and external integrations need simulator-backed testing. Do not use for human-first shell utilities, one-off scripts, or text-only CLIs.
Design stateful simulators for AI-facing CLIs that integrate with devices, networks, services, or databases. Use when a CLI needs realistic simulator-backed testing, configurable fault injection, persistent state, and a swappable adapter boundary so the same business logic runs against live and simulated backends. Do not use for shallow mocks, stateless test doubles, or CLIs with no external integration.
Critically review an existing CLI, MCP wrapper, or CLI plan for AI-first contract quality. Use when evaluating whether a CLI is JSON-first, has an MCP-ready contract seam without JSON reshaping, auditably models state changes, uses stateful simulator-backed testing for external integrations, and returns typed actionable errors. Do not use for general style review or human-first shell UX review.
Run CI quality gates with optional auto-fix and PR creation.
Run Codex tasks via the ai_cli Task Tool runner.
| name | launchpad |
| version | 0.12.0 |
| description | Use when another workflow must launch Claude, Codex, or Gemini as a separate background sub-agent without opening a terminal. Spawns the `launchpad` agent with fenced JSON input and `run_in_background: true`. |
Use this skill for pure background-agent launches. This skill is intentionally separate from any visible terminal launcher flow.
launchpad with run_in_background: true.Spawn the launchpad agent with run_in_background: true.
The launchpad agent accepts fenced JSON only. Provide one JSON object with:
{
"description": "Short launch description",
"prompt": "Task text for the child CLI",
"tool": "claude",
"model": "haiku",
"cwd": "/abs/path/to/repo",
"atm_identity": "reviewer-1",
"extra_args": ["--append-system-prompt", "Focus on tests first"]
}
Required fields:
descriptionprompttoolcwdOptional fields:
modelatm_identityextra_argsTeammate mode is enabled only when both conditions are true:
ATM_TEAMatm_identityThen the runtime:
atm teams add-member <team> <identity> --model <tool-or-model> --cwd <cwd>ATM_TEAM and ATM_IDENTITY setOtherwise the runtime:
ATM_TEAMATM_IDENTITYAll other parent environment variables are preserved for the child process.
The launchpad agent returns the runtime stdout exactly as-is. The runtime prints a JSON envelope:
{
"success": true,
"data": {
"tool": "claude",
"model": "haiku",
"cwd": "/abs/path/to/repo",
"teammate_mode": true,
"atm_team": "annotations-test",
"atm_identity": "reviewer-1",
"exit_code": 0,
"stdout": "child stdout",
"stderr": ""
},
"error": null
}
Errors use the same envelope with success: false and a populated error object.