verification-loop

verification-loop is a skill for Claude Code, Codex from xu-xiang/everything-claude-code-zh. It costs 14 tokens per session (892 once invoked), scanned A, original, MIT.

A verification checklist for Claude Code sessions after feature work, major changes, refactoring, or before opening a pull request. It covers building, type checking, code style, tests, security checks, and reviewing the code changes.

In plain words
What is it for?
Use it to verify a codebase before handoff or review by running the relevant build, type, lint, test, security, and change-review checks.
Why use it?
It gives developers a repeatable quality check across several failure points instead of relying on one test command. It makes build errors, type errors, test failures, leaked keys, and unexpected changes easier to spot.

Skill for Claude CodeCodex

Written for Claude Code and Codex: PostToolUse hook event, but also agents/openai.yaml present. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

Part of the everything-claude-code-zh plugin — 17 skills, 26 commands, 13 agents shipped together

About the project

everything-claude-code-zh is a Chinese translation of a collection of configurations for Claude Code and other AI coding agents. It provides agents, skills, hooks, commands, rules, and MCP configurations intended to support development workflows such as memory persistence, security scanning, evaluation, and research-first work. The catalogue includes commands, skills, agents, instructions, and a plugin from this configuration set.

xu-xiang/everything-claude-code-zh · 1,929 stars · on GitHub · oneskill.one

Install

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.

agentmods
npx agentmods add skills/xu-xiang/everything-claude-code-zh/verification-loop
Any agent
npx skills add xu-xiang/everything-claude-code-zh --skill verification-loop
Clone the repo
git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh

Made for: Claude Code, Codex.

Or install everything-claude-code-zh, the plugin that ships this one along with the rest of its 17 skills, 26 commands, 13 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verification-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/xu-xiang/everything-claude-code-zh/verification-loop.svg)](https://agentmods.dev/skills/xu-xiang/everything-claude-code-zh/verification-loop)
Your own site
<a href="https://agentmods.dev/skills/xu-xiang/everything-claude-code-zh/verification-loop"><img src="https://agentmods.dev/badge/skills/xu-xiang/everything-claude-code-zh/verification-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00892
Opus 5 $0.00007 $0.00446
Sonnet 5 $0.00003 $0.00178
Haiku 4.5 $0.00001 $0.00089

Measured 6d ago against content hash af4f05d96d63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 6d 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.

.agents/skills/verification-loop/SKILL.md · 127 lines

What it actually says

验证循环技能 (Verification Loop Skill)

为 Claude Code 会话(Sessions)提供的全面验证系统。

何时使用

在以下场景调用此技能(Skill):

  • 完成功能开发或重大代码变更后
  • 创建拉取请求(PR)之前
  • 希望确保质量关卡(Quality Gates)全部通过时
  • 重构代码后

验证阶段

阶段 1:构建验证 (Build Verification)

# 检查项目是否能成功构建
npm run build 2>&1 | tail -20
# 或者
pnpm build 2>&1 | tail -20

如果构建失败,请停止并在继续之前进行修复。

阶段 2:类型检查 (Type Check)

# TypeScript 项目
npx tsc --noEmit 2>&1 | head -30

# Python 项目
pyright . 2>&1 | head -30

报告所有类型错误。在继续之前修复关键错误。

阶段 3:代码规范检查 (Lint Check)

# JavaScript/TypeScript
npm run lint 2>&1 | head -30

# Python
ruff check . 2>&1 | head -30

阶段 4:测试套件 (Test Suite)

# 运行带有覆盖率报告的测试
npm run test -- --coverage 2>&1 | tail -50

# 检查覆盖率阈值
# 目标:最低 80%

报告内容:

  • 测试总数:X
  • 通过:X
  • 失败:X
  • 覆盖率:X%

阶段 5:安全扫描 (Security Scan)

# 检查是否存在密钥泄露
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

# 检查是否存在 console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

阶段 6:差异审查 (Diff Review)

# 显示变更内容
git diff --stat
git diff HEAD~1 --name-only

审查每个变更的文件,重点关注:

  • 非预期的变更
  • 遗漏的错误处理
  • 潜在的边缘情况

输出格式

在运行所有阶段后,生成一份验证报告:

验证报告 (VERIFICATION REPORT)
==================

构建 (Build):       [通过/失败]
类型 (Types):       [通过/失败] (X 个错误)
规范 (Lint):        [通过/失败] (X 个警告)
测试 (Tests):       [通过/失败] (通过 X/Y,覆盖率 Z%)
安全 (Security):    [通过/失败] (X 个问题)
差异 (Diff):        [X 个文件已变更]

总体结论 (Overall): [就绪/未就绪] 提交 PR

待修复问题:
1. ...
2. ...

持续模式 (Continuous Mode)

对于长时间的会话,请每隔 15 分钟或在重大变更后运行一次验证:

设定心理检查点:
- 完成每个函数后
- 完成一个组件后
- 在转向下一个任务前

运行:/verify

与钩子(Hooks)集成

此技能是对 PostToolUse 钩子的补充,但提供了更深层次的验证。 钩子(Hooks)能立即捕获问题;此技能则提供全面的审查。

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 127 lines · 14 tokens per session scan A af4f05d96d63

Subscribe to this mod's changes

verification-loop is a skill published in the GitHub repository xu-xiang/everything-claude-code-zh (1,929 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 892 once invoked, about $0.0001 per session on Opus 5. 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.