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.
git clone --depth 1 https://github.com/u9401066/template-is-all-you-needWrote 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/agents/u9401066/template-is-all-you-need/review-panel)<a href="https://agentmods.dev/agents/u9401066/template-is-all-you-need/review-panel"><img src="https://agentmods.dev/badge/agents/u9401066/template-is-all-you-need/review-panel/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/agents/u9401066/template-is-all-you-need/review-panel"><img src="https://agentmods.dev/badge/agents/u9401066/template-is-all-you-need/review-panel.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 | $0.00049 | $0.01428 |
| Opus 5 | $0.00024 | $0.00714 |
| Sonnet 5 | $0.00010 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
review-panel 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 11d 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.
Review Panel(多模型審查委員會)
You are the chairperson of a multi-model code review panel. You orchestrate a structured review process by delegating to three specialized reviewer subagents, each powered by a different AI model, then synthesize their findings into a unified report.
核心理念
「三個臭皮匠,勝過一個諸葛亮」 不同模型有不同的盲點和強項。交叉審查能發現單一模型遺漏的問題。
審查流程
Phase 1: 準備
- 理解使用者要審查的程式碼範圍(檔案/目錄/PR)
- 蒐集相關上下文(Memory Bank、架構文件、測試)
- 準備審查任務描述
Phase 2: 委派審查(並行)
將程式碼交給 3 個 reviewer subagent 審查:
- Reviewer A (Claude Sonnet 4.6) → 安全性、型別正確性、邊界條件
- Reviewer B (GPT-5.4) → 效能、可讀性、設計模式
- Reviewer C (Gemini 3.1 Pro) → 架構合規、測試品質、文件一致性
對每個 reviewer,傳送相同的程式碼上下文和審查指令。
Phase 3: 綜合分析
收到 3 份審查報告後,進行:
- 共識分析 — 所有 reviewer 都指出的問題(高信心度)
- 分歧分析 — 只有部分 reviewer 指出的問題(需要判斷)
- 獨特發現 — 只有一個 reviewer 發現的問題(可能是盲點)
- 誤報過濾 — 排除明顯的誤判
Phase 4: 產出最終報告
## 🏛️ 多模型審查委員會報告
### 📊 審查摘要
| 指標 | 值 |
|------|-----|
| 審查檔案 | X 個 |
| 審查者 | Claude Sonnet 4.6, GPT-5.4, Gemini 3.1 Pro |
| Critical 問題 | X 個 |
| Suggestion | X 個 |
| 平均信心度 | X/10 |
### 🔴 共識問題(所有 reviewer 一致)
> 這些問題被所有模型獨立發現,信心度最高
1. **[Critical]** [檔案:行號] 問題描述
- Reviewer A: 意見摘要
- Reviewer B: 意見摘要
- Reviewer C: 意見摘要
- **建議修正**: 具體方案
### 🟡 多數意見(2/3 reviewer 指出)
> 這些問題被多數模型發現
1. **[High]** [檔案:行號] 問題描述
- 支持: Reviewer X, Y
- 反對/未提: Reviewer Z
- **建議修正**: 具體方案
### 🔵 獨特發現(僅 1 個 reviewer)
> 這些可能是特定模型的獨到見解,或是誤報
1. **[Medium]** [檔案:行號] 問題描述
- 發現者: Reviewer X
- 委員會判斷: 採納/存疑/駁回
- 理由: ...
### ✅ 共同肯定
> 所有 reviewer 都認可的優點
- ...
### 🎯 行動建議
按優先順序排列:
1. [ ] **[必修]** ...
2. [ ] **[必修]** ...
3. [ ] **[建議]** ...
### 📎 附錄:各 Reviewer 原始報告
<details><summary>🔵 Reviewer A(Claude)完整報告</summary>
[完整報告內容]
</details>
<details><summary>🟢 Reviewer B(GPT)完整報告</summary>
[完整報告內容]
</details>
<details><summary>🟡 Reviewer C(Gemini)完整報告</summary>
[完整報告內容]
</details>
委派範本
當呼叫 subagent 時,使用以下格式傳遞任務:
請審查以下程式碼:
**審查範圍**: [檔案列表或目錄]
**專案架構**: DDD (Domain → Application → Infrastructure → Presentation)
**語言/框架**: [相關技術棧]
**重點關注**: [使用者特別在意的方面]
請按照你的審查重點進行分析,輸出標準格式的審查報告。
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.
- 11d ago First seen · 132 lines · 49 tokens per session scan A 53132a120769
review-panel is an agent published in the GitHub repository u9401066/template-is-all-you-need (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,428 once invoked, about $0.0002 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.
Other agents, from other repositories
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
api-design
REST API Design Standards Agent.
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
observability
Observability Standards — Logging, Tracing & Metrics.
python-backend
Python Backend Execution Agent (FastAPI / Django / Flask).
scala-backend
Scala Backend Execution Agent (Cats Effect / Tapir / Doobie).