task-verification

task-verification is a skill for Claude Code, Codex from adamancyzhang/claude-orchestrator-server. It costs 108 tokens per session (1,930 once invoked), scanned A, original, MIT.

A checking process for comparing a builder’s completed software work with an agreed plan.

In plain words
What is it for?
Use it to inspect code changes and deliverables, run specified tests, check acceptance requirements, and write a traceable verification report.
Why use it?
It helps catch missing files, failed tests, and differences between what was requested and what was delivered.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect code changes and deliverables, run specified tests, check acceptance requirements, and write a traceable verification report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adamancyzhang/claude-orchestrator-server/task-verification
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.

Any agent
npx skills add adamancyzhang/claude-orchestrator-server --skill task-verification
Clone the repo
git clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-server

Made for: Claude Code, Codex.

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 task-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-verification.svg)](https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-verification)
Your own site
<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-verification"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,930 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00108 $0.01930
Opus 5 $0.00054 $0.00965
Sonnet 5 $0.00022 $0.00386
Haiku 4.5 $0.00011 $0.00193

Measured 8d ago against content hash 9b4e6e39be9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task-verification 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 8d 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.

skills/task-verification/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Verification

验证不是跑一遍测试就完了,是对照蓝图逐项核实 Builder 的产出与计划的一致性。本技能与 [[task-traceability]] 协作,确保每次验证独立、客观、可复现、可追溯——每个验证结果都可追溯到具体的验收标准。


何时触发

  • Builder 标记任务完成,责任链流转到 Verify 阶段
  • Worker 通过 claude-orchestrator claim-task 认领了 verify 类型的任务
  • 用户说"验证一下 XXX 的产出"、"检查一下有没有问题"
  • 蓝图中有 verify 类型的任务需要开工

验证六步法

按顺序执行,每一步通过才进入下一步。任一步发现偏离 → 记录问题,最终报告中体现。

1. 认领 Verify 任务并读取蓝图

# 认领验证任务
claude-orchestrator claim-task

# 读取蓝图
claude-orchestrator get-context --key plan-<目标slug>

从蓝图中提取:

  • 被验证的 Build 任务的验收标准
  • 预期的产出物类型和路径
  • 上下游依赖(谁依赖这个验证结果)

明确验证范围:只验证蓝图定义的范围内内容。不验证蓝图未定义的东西。

2. 收集 Builder 的产出物

定位 Builder 在 complete_task 中声明的产出物:

# 通过 orchestrator 或任务文档找到 Builder 的 commit hash
claude-orchestrator list-tasks --status completed | grep <task-id>

# 查看 Builder 的代码变更
git show <commit-hash> --stat
git diff <commit-hash>^..<commit-hash>

确认产出物是否存在且可访问:

  • 代码 commit 是否存在且可检出?
  • 测试报告/截图文件是否存在?
  • Builder 声明的产出物是否都可以独立检查?

如果产出物不存在或不可访问 → 立即记录为 P1 问题,退还给 Builder。

3. 逐项对照验证

按照蓝图中的验收标准,逐项独立验证(不依赖 Builder 的自测报告):

# 运行蓝图指定的测试命令
npm test -- <test-pattern> 2>&1

# 检查蓝图要求的文件产出
ls -la <expected-output-path>

# 验证代码变更是否匹配任务描述
git show <commit-hash> --name-only

对每一项验收标准记录:

  • 验收标准原文
  • 验证方法和命令
  • 实际结果
  • 判定(通过 / 偏离 / 未覆盖)

如果某项验收标准无法独立复现(如依赖 Builder 的本地环境),标记为 ⏸ 无法验证,记录原因。

4. 检查边缘情况

蓝图定义了 happy path,Verifier 检查边缘情况:

  • 异常输入的处理是否正确?
  • 边界值是否行为正确?
  • 空状态、加载中状态是否处理?
  • 与现有功能的兼容性是否被破坏?(回归测试)
  • 错误信息是否有意义?
# 运行全量测试确认无回归
npm test 2>&1 | tail -30

5. 判断偏离类型

对每个发现的问题进行分类:

类型 定义 处理
偏离 产出与蓝图不一致(少做了、做错了、多做了) 退回 Builder 修复
遗漏 蓝图的验收标准未满足 退回 Builder 补齐
越界 做了蓝图范围外的事 标记给 Reviewer 判断是否需要回退
隐患 表面上满足验收标准但存在隐蔽问题 写入验证报告,提醒 Reviewer 关注

6. 产出验证报告

写入验证报告文件(如 docs/verify/<目标slug>-YYYY-MM-DD.md):

# 验证报告

> Verifier | YYYY-MM-DD | 验证范围:Builder <name> 对 <task> 的产出

## 验证结论

(一句话:通过 / 不通过)

## 验证范围

| Build 任务 | Builder | Commit | 产出物 |
|------------|---------|--------|--------|
| <任务名> | <name> | `hash` | <path> |

## 逐项验证

| # | 验收标准 | 验证方法 | 实际结果 | 判定 |
|---|---------|---------|---------|------|
| 1 | `npm test -- auth` 通过 | 执行 `npm test -- auth` | 5/5 passed | ✅ |
| 2 | 截图 `login-flow.png` 存在 | `ls -la screenshots/` | 文件存在,尺寸 1200x800 | ✅ |
| ... | ... | ... | ... | ... |

## 问题清单

| # | 类型 | 描述 | 影响 |
|---|------|------|------|
| 1 | 遗漏 | 未实现错误重试逻辑(蓝图要求 3 次重试) | 生产环境可能因瞬时故障失败 |

## 回归检查

| 检查项 | 结果 |
|--------|------|
| 全量测试 | 42/42 passed |
| lint | 0 errors, 0 warnings |

---

*Verifier — YYYY-MM-DD*

Read the full file on GitHub · 195 lines

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. 8d ago First seen · 195 lines · 108 tokens per session scan A 9b4e6e39be9c

Subscribe to this mod's changes

task-verification is a skill published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,930 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories