Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/codelably/harmony-claude-code/verification-loopnpx skills add codelably/harmony-claude-code --skill verification-loopgit clone --depth 1 https://github.com/codelably/harmony-claude-codeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00847 |
| Opus 5 | $0.00000 | $0.00424 |
| Sonnet 5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
verification-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
驗證循環技能
Claude Code 工作階段的完整驗證系統。
何時使用
在以下情況呼叫此技能:
- 完成功能或重大程式碼變更後
- 建立 PR 前
- 想確保品質門檻通過時
- 重構後
驗證階段
階段 1:建置驗證
# 檢查專案是否建置
npm run build 2>&1 | tail -20
# 或
pnpm build 2>&1 | tail -20
如果建置失敗,停止並在繼續前修復。
階段 2:型別檢查
# TypeScript 專案
npx tsc --noEmit 2>&1 | head -30
# Python 專案
pyright . 2>&1 | head -30
報告所有型別錯誤。繼續前修復關鍵錯誤。
階段 3:Lint 檢查
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
階段 4:測試套件
# 執行帶覆蓋率的測試
npm run test -- --coverage 2>&1 | tail -50
# 檢查覆蓋率門檻
# 目標:最低 80%
報告:
- 總測試數:X
- 通過:X
- 失敗:X
- 覆蓋率:X%
階段 5:安全掃描
# 檢查密鑰
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# 檢查 console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
階段 6:差異審查
# 顯示變更內容
git diff --stat
git diff HEAD~1 --name-only
審查每個變更的檔案:
- 非預期變更
- 缺少錯誤處理
- 潛在邊界案例
輸出格式
執行所有階段後,產生驗證報告:
驗證報告
==================
建置: [PASS/FAIL]
型別: [PASS/FAIL](X 個錯誤)
Lint: [PASS/FAIL](X 個警告)
測試: [PASS/FAIL](X/Y 通過,Z% 覆蓋率)
安全性: [PASS/FAIL](X 個問題)
差異: [X 個檔案變更]
整體: [READY/NOT READY] for PR
待修復問題:
1. ...
2. ...
持續模式
對於長時間工作階段,每 15 分鐘或重大變更後執行驗證:
設定心理檢查點:
- 完成每個函式後
- 完成元件後
- 移至下一個任務前
執行:/verify
與 Hooks 整合
此技能補充 PostToolUse hooks 但提供更深入的驗證。 Hooks 立即捕捉問題;此技能提供全面審查。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 121 lines · 0 tokens per session scan A 32db6f67feec
verification-loop is a skill published in the GitHub repository codelably/harmony-claude-code (42 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 847 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…