菜单
Orchestrate the entire VERIFY phase — code review, security review, tests, run-the-app verification, and ship-prep. Use after /harness-implement. Sequences the Verify skills, runs reviewers in parallel when sensible, halts on Critical/High findings, and stops at the git boundary.
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
| name | harness-verify |
| description | Orchestrate the entire VERIFY phase — code review, security review, tests, run-the-app verification, and ship-prep. Use after /harness-implement. Sequences the Verify skills, runs reviewers in parallel when sensible, halts on Critical/High findings, and stops at the git boundary. |
Thin orchestrator over the Verify skills. Goal: prove the change is production-grade before it can merge.
Review — run /harness-claude:review (delegate to harness-claude:code-reviewer); for any
change touching auth/input/queries/files/external-calls/crypto/secrets, also
/harness-claude:security-review (delegate to harness-claude:security-reviewer); and for any
change that touched a user-facing surface (UI/page/screen/component/form/mobile/CLI-TUI),
also /harness-claude:design-review (craft + a11y/UX gate). Run the applicable reviewers in
parallel; skip the ones that don't apply and say so.
→ HALT on any Critical/High (security/correctness) or Blocker (design) finding — fix,
then re-review the changed lines.
/harness-claude:test — run the full suite (in tmux if long) + coverage. Every acceptance
criterion must have a test; coverage ≥ 80% on changed code. Add missing tests via
harness-claude:tdd-guide.
/harness-claude:verify — launch the app/feature and observe each acceptance criterion working
in reality (browser screenshot for web; exercise unhappy paths). Tests passing is
necessary, not sufficient. Anything tests missed → add a regression test (back to step 2).
/harness-claude:ship — sync docs, draft the change summary from the full diff, confirm
build/types/lint/tests green and no secrets/debug logs.
→ HALT at the git boundary: do NOT commit/push/PR. Report "ready — say the word."
Verify summary: review verdict, security verdict, design verdict (or "skipped — no UI surface"),
coverage %, observed-working evidence, docs synced, "ready to commit/PR." Then optionally
/harness-claude:harness-maintain.
Bug-fix fast lane — the entry point for fixing something already broken (a red test, a prod error, a reported defect), not building a new feature. Does the bug-specific part — reproduce as a failing test, find the root cause, write a minimal fix-plan — then hands off to the existing pipeline (/implement → /review → /security-review → /verify → /ship) so the fix rides the proven gates. The non-negotiable discipline: reproduce as a failing test FIRST, fix minimally. Opt-in; invoked explicitly. Use when something is broken and you want it fixed under the harness's gates without over-ceremonying it through /spec.
Execute a plan via test-driven development — write tests first, then minimal code, phase by phase. Use after /plan (and /architect if needed) to write the actual feature. Delegates to the harness-claude:tdd-guide agent.
Review changed code for quality, correctness, and maintainability before merge. Use immediately after implementing or modifying code. Delegates to the harness-claude:code-reviewer agent. First gate of the Verify phase.
Confirm the change actually works by running the app/feature and observing real behavior — not just that tests pass. Use late in the Verify phase, before ship. Closes the loop between "tests green" and "it works."
Orchestrate the entire IMPLEMENT phase — test-driven implementation of the approved plan, resolving build/type errors as they arise. Use after /harness-plan. Sequences /implement and /build-fix, delegates to subagents, and halts if reality diverges from the plan.
Orchestrate the entire PLAN phase in one command — spec, research, plan, plan-check, and (if warranted) architecture. Use at the start of any non-trivial feature/change. Sequences the atomic skills, delegates to subagents, and pauses for your input at each decision gate.
