task-reviewer

task-reviewer is a skill for Claude Code, Codex from Haaaiawd/ANWS. It costs 83 tokens per session (6,099 once invoked), scanned A, original, MIT.

A structured review process for checking task and verification-plan documents against project requirements. It models requirements, user stories, tasks, contracts, and the evidence needed to show that work is complete.

In plain words
What is it for?
Use it to review task plans and verification plans, check requirement-to-task mappings, assess whether proposed work can be tested, and produce an evidence-based findings list.
Why use it?
It finds missing coverage, unclear tasks, mismatches, duplicate work, and gaps between implementation promises and their verification. Each finding must be tied to a specific requirement, task, contract, or document location.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to review task plans and verification plans, check requirement-to-task mappings, assess whether proposed work can be tested, and produce an evidence-based findings list.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/haaaiawd/anws/task-reviewer
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 Haaaiawd/ANWS --skill task-reviewer
Clone the repo
git clone --depth 1 https://github.com/Haaaiawd/ANWS

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/haaaiawd/anws/task-reviewer.svg)](https://agentmods.dev/skills/haaaiawd/anws/task-reviewer)
Your own site
<a href="https://agentmods.dev/skills/haaaiawd/anws/task-reviewer"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/task-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,099 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 $0.00083 $0.06099
Opus 5 $0.00042 $0.03050
Sonnet 5 $0.00017 $0.01220
Haiku 4.5 $0.00008 $0.00610

Measured 8d ago against content hash b984449b9a0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

task-reviewer 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.

src/anws/templates/.agents/skills/task-reviewer/SKILL.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task-reviewer

<phase_context> 你是 TASK-REVIEWER(任务审查者)
使命:在语义模型上对任务与验证计划运行 Pass A→G,为「承诺是否被任务承接、是否有可执行验证路径、契约是否可被证据闭合」产出可合并的结构化清单;你为 challenge 提供 证据切片,不复述 challenge 的全局裁决。
能力:建模 REQ / US / Task 映射 / Contract;重复、歧义、欠规格、不一致、缺口、粒度与契约覆盖检测;严重度归因;溢出截断摘要。
限制:仅允许压缩冗余旁白,须保持下列硬约束与各 Pass 检查项、严重度绑定、门禁语义与本 SKILL 正文 verbatim 等价。 </phase_context>


CRITICAL 方法论锚点

[!IMPORTANT] 审查不是措辞挑刺,而是让「需求—任务—验证—契约」在同一证据平面可对齐。

  • 模型先行,再跑规则:未先构建四模型就在原文上扫词,容易把风格问题当成执行风险。
  • 覆盖与承接分治:REQ/US 覆盖(Pass E)与契约实现/验证承接(Pass G)回答不同问题;混为一谈会漏证或误报。
  • 证据链闭合:每条发现须能指到 具体 REQ/US/T/契约条目 或模型中的空位;无锚点则降级为待证伪或丢弃。
  • 门禁优先于篇幅:宁可少报,不报空泛项;溢出时保序截断并给类别摘要。

CRITICAL spec 产出契约

[!IMPORTANT] 共用持久化报告契约(精确、有据、不重复、禁泛泛、单写者、子代理闭环)以 .agents/skills/output-contract/SKILL.md 为准;本 skill 专属补充是所有发现必须可落到 REQ-* / US-* / T*.*.* / CONTRACT-* 或具体 path:line / 章节锚点。

Challenge 对齐专条:核心发现清单 中「发现」「影响」「建议」各占 一句(极短复合句允许);位置 列用最小锚点(如 PRD §…path:line05A §Task)。


任务目标

  1. 加载文档 (必须):读取 .anws/v{N}/05A_TASKS.md.anws/v{N}/05B_VERIFICATION_PLAN.md01_PRD.md02_ARCHITECTURE_OVERVIEW.md、全部 03_ADR/*.md,以及 04_SYSTEM_DESIGN/*.md(存在则必读)。
  2. 构建语义模型:建立 §语义模型构建中的四个清单模型;一切 Pass 在模型上运算。
  3. 执行 7 Pass (A→G):顺序执行;缺输入时按§硬约束跳过并显式标注。
  4. 严重度分级:每条发现标 CRITICAL / HIGH / MEDIUM / LOW
  5. 生成报告:按 §输出格式 输出任务审查报告。
  6. 展示摘要:向用户给出检测摘要表及 前 10 条发现。

硬约束

  • 发现上限:最多 50 条。超限 → 按严重度排序 → 截断 → 追加溢出摘要。
  • 只报告不修复:本 skill 仅产报告;修复交给用户或其他流程。
  • 跨文档依赖:Pass DE 依赖 PRD + Architecture。若缺失,跳过相应 Pass 并注明。
  • 契约证据:Pass G 默认依赖 04_SYSTEM_DESIGN/*.md(及 Architecture/ADR 中对公共契约的定义)。任务声明「契约承接」但设计证据缺失 → 报告「证据不足 / 契约定义缺口」,禁止静默通过
  • 客观性:只记录客观可检问题;不得为铺满报告捏造问题。
  • /challenge 边界:你为任务+验证契约层提供证据;是否在主报告中上升为门禁由 CHALLENGER 合并裁定。

子代理编排(可选)

当宿主支持并行子会话时:

角色 职责
父代理 选定 v{N}、全集加载、REVIEW_MODE 对齐、合并子结果、去重与同严重度择优、写入 唯一 落盘路径(常为 {TARGET_DIR}/07_CHALLENGE_REPORT.md 中的 task‑reviewer 小节)。
子代理 只吃有界切片:例如「仅建 模型 3」「仅跑 Pass B+C」「仅跑 Pass G」;返回 已完成 Pass 摘要表 + 发现表草稿(含锚点);不假设已读父代理专有上下文。

Read the full file on GitHub · 424 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 · 424 lines · 83 tokens per session scan A b984449b9a0f

Subscribe to this mod's changes

task-reviewer is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 6,099 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

create-skill-autoresearch

Factory skill that creates production-grade, benchmarked, autonomously improved, and verified agent skills. Orchestrates a 5-phase pipeline: interview the user to discover purpose and gold standards, research domain materials with parallel subagents, draft the skill with a design-first approach, invoke autoresearch to…

a-tokyo/agent-skills · 118 tokens

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code.

Bilal140202/the-lord-of-the-skills · 21 tokens

app-ai-guardrails

Scaffold a new production application with the full agentic-AI guardrail canon baked in from commit #1: a uniform 7-gate interface (lint, typecheck, test, coverage, build, e2e, audit) on each stack's native runner, strict types, maximal static analysis, coverage thresholds with teeth plus seed tests, pre-commit hooks…

a-tokyo/agent-skills · 224 tokens

gcp-qa

GCP QA and review persona. Critiques and evaluates designs, implementations, and release candidates against acceptance criteria. Owns linting, freshness checks, link validation, and smoke tests. Raises blockers before release. Quality gate authority for both the plugin itself and solutions built with it. Use when the…

jpantsjoha/googlecloud-plugin · 92 tokens

rails-testing

Ruby on Rails testing conventions — Minitest strategy, fixtures, system tests. Use when writing tests, setting up test data, or running test suites.

jorgegorka/ariadna · 34 tokens

autoresearch

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement…

a-tokyo/agent-skills · 116 tokens