plan-review SKILL.md skillA
plan-review from kopp0510/claude-dd is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kopp0510/claude-dd/plan-review@git:20261025.933e674Pins git:20261025.933e674 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kopp0510/claude-dd
- Path
skills/plan-review/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261025.933e674, committed Oct 25, 2026
- First version recorded
- Oct 23, 2026
- Size
- 20,679 bytes
- Repository stars
- 12
- License
- MIT
計畫的對抗式審查：派一個裁決者（Opus），由它平行派至少 3 個審查者（haiku）猛攻計畫，再逐條查證哪些批評站得住，交回主對話修正迭代。複雜任務的計畫、task-planner 的段落草稿、design-brainstorm 的設計做好之後、交出去之前自動啟用；使用者說「審計畫」「審查這個計畫」「plan review」時也啟用。不適用於程式碼 diff 的審查（用 8 步迴圈步驟 4 的 code-review）、簡單或中等任務的計畫（design-brainstorm 的設計除外）。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Plan Review — 裁決者 + 審查者的計畫審查
計畫做好後不直接交出去，先交給一個腦袋全新的裁決者。裁決者平行派審查者去證明計畫有重大缺失，
收回之後反過來查證每一條批評，只把站得住的交回來。主對話照著改，改到沒有站得住的重大缺失為止。
設計來源：`docs/designs/2026-10-23-裁決審查-design.md`（claude-dd repo）。
## 什麼時候跑
| 情境 | 跑不跑 |
|---|---|
| 全域 §4.1 的複雜任務（N = 1；N ≥ 2 等 `task-planner` 出草稿時再跑），計畫寫好、要交出去之前 | 跑 |
| `task-planner` 步驟 4，草稿（進度表、小任務、測試清單）出好之後 | 跑 |
| `design-brainstorm` 設計逐段整理好、離開 plan mode 之前 | 跑 |
| 使用者說「審計畫」「審查這個計畫」 | 跑 |
| 簡單、中等任務 | 不跑（但走 `design-brainstorm` 的設計不論大小都跑） |
| 審程式碼 diff | 不跑（那是步驟 4 的 code-review） |
## 步驟
### 1. 準備交給裁決者的東西
- **審查範圍**：這次要審的是什麼（整份計畫，或某份文件的某一段）。只審一段時寫明「其他段落是背景，不在範圍內」，
這句同時寫進「事實」開頭（「審查範圍」那一欄審查者看不到）
- **計畫全文**：照要交給使用者的版本，一字不改。計畫引用或依賴別處的段落（「見設計決策」、上層的設計決策表、
它依賴的段落），把那幾段一起附上，標「附錄：<出處>」；整份大文件放不下時，附路徑讓審查者自己讀
- **已查到的事實**：讀過哪些檔（路徑）、實跑過的指令與輸出、使用者在對話裡講定的決定（逐條，標「使用者決定」）
- **只交事實，不交「我判斷 X 是原因」**。要寫推測就標明是推測 —— 裁決者與審查者會跟著錯的框架走
- **第 2 輪以後**：再附上前幾輪的裁決報告全文、「這輪改了哪裡」的清單、前幾輪外部查證的結果、前幾輪還沒問使用者的「需使用者決定」
- **輪次**：這是第幾輪（從 1 開始）
- 專案根目錄的絕對路徑（審查者要自己 grep）
### 2. 派裁決者
用 Agent 工具：`subagent_type: "general-purpose"`、`model: "opus"`，prompt 用下面的「裁決者範本」。
**主對話只填 `{…}`**（範圍、計畫、事實、輪次、根目錄）；範本裡的 `《…》` 是留給裁決者填的，原樣保留。
…Read the whole file at its exact version.
How to install
mdr add kopp0510/claude-dd/plan-review@sha256:8990685e226d1f08The line at the top of this page pins the label git:20261025.933e674, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qsvytexvjqnq5yyc)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Oct 23, 2026 and Oct 25, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261025.933e674 latest | 2026-10-25 | 933e674 | 20,679 B | A | view · diff |
| git:20261025.04fa095 | 2026-10-25 | 04fa095 | 19,639 B | A | view · diff |
| git:20261025.1dcdba3 | 2026-10-25 | 1dcdba3 | 18,736 B | A | view · diff |
| git:20261024.efb7931 | 2026-10-24 | efb7931 | 17,531 B | A | view · diff |
| git:20261024.6962874 | 2026-10-24 | 6962874 | 17,162 B | A | view · diff |
| git:20261023.c5464d4 | 2026-10-23 | c5464d4 | 15,754 B | A | view · diff |
| git:20261023.dfa7a77 | 2026-10-23 | dfa7a77 | 15,566 B | A | view · diff |
| git:20261023.d69781b | 2026-10-23 | d69781b | 13,877 B | A | view · diff |
| git:20261023.199ed37 | 2026-10-23 | 199ed37 | 13,835 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (20679 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kopp0510/claude-dd · 12 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qsvytexvjqnq5yyc GET https://markdownregistry.com/api/v1/resolve?ref=kopp0510/claude-dd/plan-review GET https://markdownregistry.com/api/v1/blob/8990685e226d1f0856b5cf2ccd3f0dc46921da2a60c369b0367a35047ae19b1a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from kopp0510/claude-dd
Every file in kopp0510/claude-dd