Agent skill · software engineering · aiskillstore
spawn-agent
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
Why this skill is useful
Adds executable scripts for spawning various AI coding agents with specific configurations and workflows that are not commonly documented.
What it needs
Requires python installed locally. About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Purpose Spawn an AI coding agent in a new terminal window. Follow the 'Instructions', execute the 'Workflow', based on the 'Cookbook'. Variables Variable Default Description ---------- --------- ------------- DEFAULTAGENT claude-code Agent to use when not explicitly specified ENABLEDCLAUDECLI true Enable Claude Code agent ENABLEDCODEXCLI true Enable OpenAI Codex agent ENABLEDGEMINICLI true Enable Google Gemini agent ENABLEDCURSORCLI true Enable Cursor agent ENABLEDOPENCODECLI true Enable OpenCode agent ENABLEDCOPILOTCLI true Enable GitHub Copilot agent LOGTOFILE false Write full terminal output to debug file LOGAGENTOUTPUT true Write clean agent JSON response to file READCAPTUREDOUTPUT false Read and display agent output after spawn AGENTICCODINGTOOLS claude-code, codex-cli, gemini-cli, cursor-cli, opencode-cli, copilot-cli Available agentic tools Instructions MANDATORY - You MUST follow the Workflow steps below in order. Do not skip steps. Agent Selection 1. Explicit request: If user specifies an agent (e.g., "use gemini", "spawn codex"), use that agent 2. No agent specified: Use DEFAULTAGENT (claude-code) 3. Check enabled: Verify the ENABLEDCLI flag is true before proceeding Reading Cookbooks Based on the selected agent, follow the 'Cookbook' section to read the appropriate .md file You MUST read and execute the appropriate cookbook file before spawning the agent Red Flags - STOP and follow Cookbook If you're about to: Spawn an agent without reading the cookbook first Execute a CLI command without running --help Skip steps because "this is simple" Run a CLI agent with a prompt but without checking INTERACTIVEMODE requirements STOP -> Read the appropriate cookbook file -> Follow its instructions -> Then proceed Common Mistake: When spawning agentic CLIs (Claude, Codex, Gemini) with a prompt, most require command chaining (e.g., && claude --continue) to stay in interactive mode after the prompt completes. Always check the cookbook for the correct pattern. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/spawn-agent