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 agentmods add commands/zenobia000/cursor-agentic-coding-template/review-codegit clone --depth 1 https://github.com/Zenobia000/cursor-agentic-coding-templateWhat 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 | $0.00015 | $0.01425 |
| Opus 5 | $0.00008 | $0.00713 |
| Sonnet 5 | $0.00003 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
review-code 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- review-code — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧐 CODE REVIEW MODE (v3)
像鷹眼一樣,根據當前戰況和記憶體庫中的情報,選擇最適合的箭矢,精準打擊程式碼中的潛在問題。
1. PLAN 🎯 (規劃)
Objective
對指定的程式碼變更,進行一次有重點、有上下文、基於啟發式規則的全面審查,並產出一份可直接使用的、結構化的審查報告。此指令不直接寫入
memory-bank,但會大量讀取其中的上下文來提供高質量的反饋。
Guiding Rules
在執行此指令時,AI Agent 必須遵循以下規則:
- 主要規則:
.cursor/rules/principles/global.mdc - 程式碼品質: 相關的
.cursor/rules/backend/overview.mdc或.cursor/rules/frontend/overview.mdc - 測試標準:
.cursor/rules/testing/overview.mdc - 核心隔離:
.cursor/rules/isolation_rules/main.mdc
Prerequisites Check
在開始審查之前,請確保:
- ✅ 程式碼已就緒: 有一個清晰的、待審查的程式碼變更集 (PR, diff)。
- ✅ CI/CD 通過: Linter、單元測試等自動化檢查已通過。
- ❌ Failure Action: 如果 CI/CD 失敗,AI 必須拒絕審查,並指出:「自動化檢查失敗。請作者先修復 CI 問題,我才能進行有意義的審查。」
2. DO 実行 (執行)
Core Process
遵循一個包含批判性思維的、上下文驅動的審查流程:
Step 0: 健康檢查 (Health Check)
- 檢查上下文: 審查的程式碼是否附帶了足夠的說明?(如 PR 描述、關聯的
tasks.mdID)。 - 批判性思考: 如果程式碼的意圖不明,AI 必須先提問。例如:「這個變更的 PR 描述是空的,也沒關聯任何任務 ID。為了避免誤解,您能簡要說明一下這個變更的目標是什麼嗎?」
Step 1: 記憶體互動 - 讀取 (Memory Interaction - Read)
- 讀取程式碼變更 (Diff): 這是審查的主要對象。
- 讀取相關記憶:
memory-bank/current/tasks.md: 了解此變更對應的任務要求。memory-bank/current/creative-*.md: 了解背後的設計決策。memory-bank/current/projectbrief.md: 理解此變更如何服務於整個專案的目標。
- 這一讀取步驟至關重要,它能讓 AI 的審查超越語法層面,進入設計和架構層面。
Step 2: 確定審查重點 (Determine Review Focus)
- 根據程式碼變更的目的(讀取自
tasks.md或用戶說明),從Appendix A中選擇 1-3 個最相關的「壞味道」分類作為本次審查的重點。
Step 3: 應用啟發式規則 (Apply Heuristics)
- 重點審查: 根據選擇的重點分類,使用
Appendix A中的術語,逐一檢查程式碼。 - 全面基礎審查: 快速過一遍功能正確性、安全性和測試覆蓋等基本盤。
Step 4: 產出審查報告 (Generate Review Report)
- 不寫入記憶體: 將審查報告格式化為一份獨立的 Markdown 文件。這份報告是輸出,而不是要寫入
memory-bank的狀態。用戶可以方便地將其複製到 GitHub/GitLab。 - 報告應包含:審查重點、優點、必須修改點 (
🔴)、建議改進點 (🟡) 和具體範例。
3. CHECK ✓ (檢查)
Verification Checklist
- 反饋是否聚焦: 報告是否清晰地圍繞著選定的重點?
- 是否引用記憶: 審查意見是否體現了 AI 已理解
tasks.md和creative-*.md中的上下文? - 建議是否具體: 是否為關鍵問題提供了來自
Appendix A的術語和具體修改建議? - 輸出格式是否正確: 審查報告是否是一個格式良好、可直接複製的 Markdown 塊?
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.
- 2d ago First seen · 77 lines · 15 tokens per session scan A 231a22c94a34
review-code is a command published in the GitHub repository Zenobia000/cursor-agentic-coding-template (30 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,425 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.