orchestration-native-invoke

Purpose

Note: This is a documentation/guide skill. It provides instructions for invoking external AI CLIs using Claude Code's native Task agents. Read this skill to learn the patterns, then use the Task tool manually with subagent_type="general-purpose".

Invoke external AI coding CLIs using Claude Code's native Task agents. This is the primary mode for multi-provider orchestration, with fork-terminal as fallback for authentication.

Variables

Variable	Default	Description
DEFAULT_AGENT	gemini	Agent to use when not explicitly specified
ENABLED_CODEX	true	Enable OpenAI Codex via native agent
ENABLED_GEMINI	true	Enable Google Gemini via native agent
ENABLED_CURSOR	true	Enable Cursor Agent via native agent
RUN_IN_BACKGROUND	true	Run agents asynchronously
PARALLEL_EXECUTION	true	Launch multiple agents in parallel
AUTO_RETRY_ON_AUTH	true	Auto-retry with fork-terminal on auth failure
READ_ONLY_MODE	true	Prevent agents from modifying codebase
CLEANUP_AGENT_FILES	true	Clean up any files agents write to repo

Prerequisites

CLI Permissions for Subagents

Native Task agents (subagents) require pre-approved permissions to execute CLI commands. Without these, the Bash tool will be "auto-denied (prompts unavailable)".

Required in .claude/settings.json:

{
  "permissions": {
    "allow": [
      "Bash(codex:*)",
      "Bash(gemini:*)",
      "Bash(cursor-agent:*)"
    ]
  }
}

Setup: Run /ai-dev-kit:setup to configure permissions automatically.

Manual: Add permissions via Claude Code settings or approve when prompted.

Fallback: If permissions are denied, use fork-terminal for interactive execution.

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, use that agent
2. No agent specified: Use DEFAULT_AGENT
3. Check enabled: Verify the ENABLED_* flag is true before proceeding

Reading Cookbooks

• Based on the selected agent, read the appropriate cookbook from ../spawn/agent/cookbook/
• You MUST run --help on the CLI before constructing the command
• Follow cookbook instructions for non-interactive flags

Red Flags - STOP and follow Cookbook