메뉴
Classify tools, skills, commands, and external actions by risk level and define required approvals or guardrails before execution. Use whenever a run may invoke unfamiliar tooling, destructive actions, broad write scope, or external systems.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Turn a structured intake artifact into a decision-complete plan, task graph, dependency map, owned paths, acceptance checks, expected outputs, and retry assumptions. Use when work spans multiple steps, files, or roles and needs explicit orchestration.
Assemble the final deliverable, orchestration log, vetter report, and concise retrospective for a completed orchestrated run. Use when implementation and review are complete and results need to be packaged clearly.
Assign work packages by role, enforce owned-path boundaries, manage execution state, track retries, blockers, review readiness, and host-driven ledger updates. Use when work is being handed off across phases or subagents.
Bridge OpenSpec change artifacts into Ultra-Orchestrator execution artifacts. Use when a repo follows OpenSpec for proposal, design, tasks, and archive, but execution should remain controlled by Ultra-Orchestrator through TaskManifest, WorkPackage, review, QA, risk gates, and ledger-based orchestration.
Legacy compatibility entry point for the original Ultra Orchestrator flow. Use only when you need the older lightweight stage-based orchestration behavior without the new strict OpenSpec-first control plane.
Primary Ultra Orchestration entry point for strict Codex-controlled engineering runs. Use this single skill for development, bug fixes, OpenSpec work, multi-file implementation, review/QA-heavy tasks, risk-gated work, or any run that needs automatic mode selection, OpenSpec bootstrap, machine-checkable TaskManifest and WorkPackage artifacts, ledger tracking, slice DAG execution, review, QA, delivery evidence, and retro.
| name | risk-vetter |
| description | Classify tools, skills, commands, and external actions by risk level and define required approvals or guardrails before execution. Use whenever a run may invoke unfamiliar tooling, destructive actions, broad write scope, or external systems. |
Classify execution risk before the orchestrator crosses a safety boundary.
LOWMEDIUMHIGHEXTREMEReturn:
risk_levelchecked_itemsdecisionsrequired_guardrailsapproval_needed