Collab Deliberation

Use this skill when the user asks for brainstorming, tradeoffs, option comparison, or decision support before implementation. This skill is for ideas and decisions, not coding.

Terminology + feature gate (required)

• In this skill, "collab" means multi-agent tool usage (spawn_agent / wait / close_agent).
• Codex CLI feature gating is features.multi_agent=true; treat collab as legacy naming in some env/artifact keys.
• For symbolic orchestration, existing key names remain RLM_SYMBOLIC_COLLAB and manifest.collab_tool_calls.

Deliberation Default v1 (required)

• Keep MCP as the lead control plane. Use collab/delegated subagents to generate and challenge options.
• Run full deliberation when any hard-stop trigger is true:
  • Irreversible/destructive change with unclear rollback.
  • Auth/secrets/PII boundary touched.
  • Direct production customer/financial/legal impact.
  • Conflicting intent on high-impact work.
• Otherwise compute a risk score (0..2 each): reversibility, external impact, security/privacy boundary, blast radius, requirement clarity, verification strength, time pressure.
• Run full deliberation when score >=7 or two or more criteria score 2.
• Use these time budgets for auto-deliberation: