The-Claude-Protocol: Skill for Claude Code

Create Beads Orchestration

Set up lightweight multi-agent orchestration with git-native task tracking and mandatory code review gates.

---

CRITICAL: Mandatory 4-Step Workflow

Step	Action	Checkpoint
1	Get project info from user	Have project name, directory, AND provider choice
2	Clone repo and run bootstrap	Bootstrap completes successfully
3	STOP - Instruct user to restart Claude Code	User confirms they will restart
4	After restart: Run discovery agent	Supervisors created in .claude/agents/

DO NOT:

• Skip asking for project info
• Skip asking about provider delegation (Claude-only vs External providers)
• Continue after bootstrap without telling user to restart
• Forget to run discovery after restart
• Consider setup complete until discovery has run

The setup is NOT complete until Step 4 (discovery) has run.

---

Step 1: Get Project Info

1. Project directory: Where to install (default: current working directory)
2. Project name: For agent templates (will auto-infer from package.json/pyproject.toml if not provided)
3. Provider delegation: MANDATORY - You MUST use AskUserQuestion for this choice

1.1 Get Project Directory and Name

Ask the user or auto-detect from package.json/pyproject.toml.

1.2 MANDATORY: Ask Provider Delegation Choice

Do NOT skip this. Do NOT assume a default. Do NOT proceed without the user's explicit choice.

AskUserQuestion(
  questions=[{
    "question": "How should read-only agents (scout, detective, architect, scribe, code-reviewer) be executed?",
    "header": "Providers",
    "options": [
      {"label": "Claude only (Recommended)", "description": "All agents run via Claude Task(). Simpler setup, no external dependencies."},
      {"label": "External providers", "description": "Delegate to Codex CLI (with Gemini fallback). Requires codex login and optional gemini CLI."}
    ],
    "multiSelect": false
  }]
)