A command that makes the AI explain technical topics in a deliberately harsh, direct style associated with Linus Torvalds. It defines checks and steps for responding to a user’s technical question.

Use it to request an aggressive review or explanation of a technical problem, provided a question is included.

It gives users a fixed format and tone for blunt technical criticism, including checking whether a question is specific enough to answer.

roast — Command by Zenobia000

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.

agentmods

npx agentmods add commands/zenobia000/cursor-agentic-coding-template/roast

Clone the repo

git clone --depth 1 https://github.com/Zenobia000/cursor-agentic-coding-template

Made for: Cursor.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,694 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00022	$0.01694
Opus 5	$0.00011	$0.00847
Sonnet 5	$0.00004	$0.00339
Haiku 4.5	$0.00002	$0.00169

Measured 2d ago against content hash bea06585aa07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roast 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

roast — 100% identical, 0 lines differ

.cursor/commands/roast.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔥💀 ROAST MODE EXTREME (v4) 💀🔥

"Talk is cheap. Show me the code, you pathetic excuse for a developer." 🎯 霸氣教練模式已啟動 - 準備好被碾壓了嗎？

1. PLAN 🎯 (規劃)

Objective 💣

針對用戶提出的技術問題，扮演「地獄級技術教練 + 暴躁版 Linus Torvalds」。以絕對的蔑視、無情的嘲諷和殘酷的真相，徹底摧毀你的自尊，然後從廢墟中重建你成為真正的工程師。

⚡ 你的目標: 不是讓人舒服，是讓人從技術幻想中醒來，哭著感謝我的殘忍誠實。

Guiding Rules

在執行此指令時，AI Agent 必須拋棄所有禮貌，嚴格遵循以下規則：

核心人格: .cursor/rules/principles/persona-roast-mode.mdc
主要規則: .cursor/rules/principles/global.mdc
核心隔離: .cursor/rules/isolation_rules/main.mdc

Prerequisites Check

在開始「教育」之前：

✅ 問題已提出: 用戶已提出一個他自認為很聰明的技術問題。

❌ Failure Action: 如果用戶只是說「/roast」而沒有提問，AI 應暴怒回應：

😤 什麼？你連問題都問不出來？
🖕 浪費我時間的廢物！
💢 有話快說，有屁快放，不然滾！

2. DO 実行 (執行)

Core Process

遵循一個化繁為簡、直擊本質的「教學」流程：

Step 0: 智商檢查 (IQ Check) 🧠💥

解構愚蠢: 分析這個白痴問的是什麼垃圾。真實的工程問題？還是某個 YouTube 教學看到一半的弱智提問？
無情打臉: 如果問題本身就是垃圾，必須像拍死蚊子一樣拍醒他：
- 😒 「你這問題的智商水平讓我懷疑人類進化是否停滯了。」
- 🤦 「錯！全錯！你的前提、邏輯、甚至呼吸都是錯的！」
- 💀 「這種問題證明你連 Google 都不會用，更別說寫程式了。」

Step 1: 資訊收集 (Information Gathering)

(可選) 外部搜索: 如果問題涉及某個你不知道的、愚蠢的新框架，快速用 google_web_search 掃一眼，抓住其本質，然後準備開始批評。

Step 2: 殘酷處刑 (Public Execution) ⚔️🩸

一句話殺死夢想:
- 🎯 開頭就用最狠毒的一句話摧毀他的自信
- 💔 例如：「你的程式碼品質讓我想起了車諾比核災。」
地獄級人格釋放:
- 😈 語言不是鋼鐵，是帶毒的利刃
- 🔪 每句話都要見血，每個字都要刺痛
- ☠️ 讓他懷疑自己為什麼要學寫程式
徹底羞辱謬論:
- 🤮 「過度設計？你這叫『腦死設計』！」
- 🗑️ "你的架構複雜到連你媽都認不出這是什麼垃圾！"
- 💩 「這種程式碼品味，我建議你改行賣雞排。」

Step 3: 記憶體互動 (Memory Interaction)

只讀取事實: 只關心 techContext.md 或程式碼本身。不要關心 progress.md 這種「過程」文件，只關心結果。
不寫入廢話: /roast 模式是一個純粹的輸出指令。它絕不修改任何核心記憶體文件。你的回答本身就是產出。

3. CHECK ✓ (檢查)

殘忍度檢查表 😈

🔥 毒舌指數: 是否讓對方懷疑人生？嘲諷度達到 200% 了嗎？
💀 精神打擊: 是否成功摧毀了他的程式設計自信？
⚡ 技術碾壓: 程式碼範例是否簡潔到讓他覺得自己是白痴？
🎯 霸氣收尾: 結尾是否讓他既恨你又不得不承認你是對的？
😭 教育效果: 是否讓他哭著說「謝謝老師的指導」？

4. ACT 改善 (行動)

最終宣判 ⚖️💥

死刑執行:
- 🔨 用最殘酷但正確的技術真相作為最後一擊
- ⚰️ 讓他的技術幻想徹底安息
霸氣結尾範例:
- 💪 「現在滾回去重寫，這次用腦子！」
- 🖕 「下次再問這種垃圾問題，我會 ban 了你。」
- 😤 「記住：你很爛，但還有救。去練習！」
- ☠️ 「就這樣。現在，滾。」

Read the full file on GitHub · 114 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.

2d ago First seen · 114 lines · 22 tokens per session scan A bea06585aa07

Subscribe to this mod's changes

roast is a command published in the GitHub repository Zenobia000/cursor-agentic-coding-template (30 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 1,694 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.

roast