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 skills add Stanshy/AgentHub --skill reviewgit clone --depth 1 https://github.com/Stanshy/AgentHubWrote 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.
[](https://agentmods.dev/skills/stanshy/agenthub/review)<a href="https://agentmods.dev/skills/stanshy/agenthub/review"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stanshy/agenthub/review"><img src="https://agentmods.dev/badge/skills/stanshy/agenthub/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.01921 |
| Opus 5.5 | $0.00007 | $0.00768 |
| Sonnet 5.5 | $0.00004 | $0.00384 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
review 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
L1 內部 Review
執行內部 Review checklist 並記錄到開發計畫書第 10 節。支援自動偵測步驟類型。
使用方式
/review [review-type] [target]
參數
$0: Review 類型（auto / code / spec / design / function）$ARGUMENTS: 完整參數- 若
$0為auto或省略，自動偵測當前步驟
步驟自動偵測
當 review-type 為 auto 或未指定時：
- 讀取
proposal/sprint*-dev-plan.md（最新的開發計畫書） - 找到第 10 節「執行紀錄」中最近完成的任務
- 根據任務類型判斷步驟：
- 含
design/架構/API 設計→ 步驟 = 設計 → Review: 對規範 - 含
mockup/UI/圖稿→ 步驟 = UI 圖稿 → Review: 對設計稿 - 含
backend/API/route/service→ 步驟 = 實作（後端）→ Review: 對程式碼 + 對規範 - 含
frontend/component/view/page→ 步驟 = 實作（前端）→ Review: 對程式碼 + 對設計稿 + 對規範 - 含
test/e2e/spec→ 步驟 = 測試 → Review: 對功能 + 對規範 - 含
doc/文件→ 步驟 = 文件 → Review: 對規範
- 含
- 輸出偵測結果，確認後執行
Review Checklist
對程式碼（code）
- 無 bug 或邏輯錯誤
- 錯誤處理完整（外部呼叫有 try-catch）
- 無硬編碼機密資訊
- 命名有意義且符合規範（snake/camel/Pascal 分層）
- 無死碼（註解掉的程式碼、未使用的 import）
- 單一職責原則
- TypeScript 型別正確（無 any）
- 文件已同步更新（.knowledge/ + CLAUDE.md 索引）
對規範（spec）
- 實作與 API 規範文件一致（api-design.md）
- 實作與 data model 文件一致（data-model.md）
- 實作與 feature spec 一致（feature-spec.md）
- 命名轉換正確（DB snake → API snake → 前端 camel）
對設計稿（design）
- 佈局結構一致（元件位置、大小、間距）
- 色彩一致（使用設計稿色系，未自行選色）
- 動畫一致（時長、easing 與設計稿規格相符）
- 狀態切換完整（設計稿定義的每個 UI 狀態都已實作）
- 響應式一致（桌面版和手機版都與設計稿一致）
- 文案一致（按鈕文字、placeholder、空狀態文案）
L1 比對方式：同時開啟設計稿 HTML/截圖和實際畫面，逐項確認。UI 不一致 = Blocker。
對功能（function）
- 端到端功能正常
- 效能達標
- 驗收標準全部滿足
- 無 Critical/High 等級 Bug
對文件正確性（doc-integrity）
檢查 dev-plan 和 .tasks/ 檔案的格式與內容一致性。 觸發時機：每次
/review時自動附加執行，不需手動指定。
dev-plan 檢查
- 第 10 節存在且包含三個子表格（任務完成紀錄、Review 紀錄、Gate 紀錄）
- Gate 紀錄的決策值符合規範（
✅ 通過/❌ 駁回/⚠️ 附條件通過，不可用純文字或英文） - 日期格式為
YYYY-MM-DD - 第 6 節任務表與
.tasks/目錄的任務數量一致
task 文件檢查（逐一掃描 .tasks/sprint-{N}/*.md）
- metadata 表必要欄位齊全：ID、狀態、Sprint、建立時間、開始時間、完工時間
- 狀態值為合法英文值（created / assigned / in_progress / in_review / done / blocked / rejected）
- 事件紀錄區塊（
## 事件紀錄）存在且至少有一筆紀錄 - 事件紀錄 timestamp 格式為 ISO 8601（
YYYY-MM-DDTHH:mm:ss.sssZ） - 狀態為
done的任務，驗收標準全部打勾（- [x]，無殘留- [ ]） - 狀態為
in_progress以上的任務，開始時間不得為— - 狀態為
done/in_review的任務，完工時間不得為—
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.
- 1mo ago First seen · 132 lines · 18 tokens per session scan A 486f77bbc4f6
review is a skill published in the GitHub repository Stanshy/AgentHub (204 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,921 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
update-pr
Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.
code-reviewer
Default code-quality route for broad code review, PR review, maintainability, correctness, and regression-risk checks. Do not use as the primary route for dedicated OWASP/security audits, review-feedback handling, completion verification, AI-code cleanup, or TDD/test-first work.
comet-review
A read-only review guide for checking the current Comet change, a managed software-change workflow. It focuses on correctness, security, and boundary problems without changing files or advancing the workflow.
deslop
Remove AI-generated code slop from a branch: unnecessary comments, redundant defensive checks, boilerplate, style drift, and type casts. Use for cleanup of AI-written code, not for broad code review, security audit, TDD, or final verification.
comet-github-pr-review
A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.
winui-code-review
Review WinUI 3 code or changes for quality: MVVM, x:Bind correctness, accessibility, theming, security, performance, and WinUI analyzer findings. Use when asked to review or audit a WinUI app or its pending changes, or before committing. Catches issues the compiler and UI tests miss.