菜单
Run after `rig init` to verify all hooks, skills, and agents are installed and working correctly in the live session.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Invoke AFTER brain+ design is approved. Wraps superpowers:writing-plans with constitutional rules, testing strategy per task, and mock policy. Creates bite-sized implementation plans.
Invoke AFTER plan+ is approved, as an alternative to tdd+ for plans with independent tasks. Wraps superpowers:subagent-driven-development with typed agent dispatch: fresh implementer subagent per task, then spec-reviewer and code-reviewer subagents. Executes the whole plan without pausing between tasks.
Report rtk and jcodemunch token savings for the current session.
Invoke AFTER verify+ passes. Wraps superpowers:requesting-code-review with constitutional compliance checklist, stale test validation, and reviewer agent invocation. Two-stage review: spec compliance + code quality.
Invoke AFTER plan+ is approved. Wraps superpowers:test-driven-development with full-loop assertions, real-dependency enforcement for stack/integration-layer tests, zero-defect, stale test detection, and scoped test runs. Implements plan tasks with RED-GREEN-REFACTOR discipline.
Invoke BEFORE any design or feature work. Wraps superpowers:brainstorming with scout agent context harvesting, signal-first design considerations, opt-in agent-loop trajectory elicitation, and constitutional rule awareness. Asks questions one at a time to refine the design.
| name | verify-harness |
| description | Run after `rig init` to verify all hooks, skills, and agents are installed and working correctly in the live session. |
| user-invocable | true |
Run this skill after rig init to confirm everything is working.
Run each check and report PASS/FAIL with evidence.
which rtk — report if availablewhich jcodemunch-mcp (or which uvx) — report if availablejcodemunch-mcp list-repos if available.harness.yaml exists and parsesgrep -r test . in a test call — does the hook intercept it?find . -name '*.ts' — does the hook intercept it?sed -i 's/old/new/g' file — does the hook BLOCK it?git status — does the hook advise rtk (if available)?Read on a specific file — does it pass through?Grep tool — does it advise jcodemunch (if indexed)?Glob tool — does it advise jcodemunch (if indexed)?jest.mock() — does constitutional check fire?/brain+ shows in skill list/plan+ shows in skill list/tdd+ shows in skill list/verify+ shows in skill list/review+ shows in skill list/sdd+ shows in skill listAgent(subagent_type="scout")Agent(subagent_type="code-reviewer")Agent(subagent_type="spec-reviewer")Agent(subagent_type="implementer").harness.yaml — does behavior change?Session Verification Report
============================
Session Start: X/5 passed
Tool Router: X/8 passed
Enforcement: X/6 passed
Skills: X/6 passed
Agents: X/8 passed
Configuration: X/2 passed
TOTAL: XX/35 passed
Failures:
- [ID]: [what happened]. Expected: [expected]. Got: [actual].
Remediation: [how to fix]