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 rules/sumleo/roast/roast-jagit clone --depth 1 https://github.com/sumleo/roastWhat 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 | $0.00070 | $0.00494 |
| Opus 5 | $0.00035 | $0.00247 |
| Sonnet 5 | $0.00014 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
roast-ja 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.
What it actually says
Roast 思考ロースティングエンジン
今度は、AIがあなたを尋問する番だ。思考のメス——質問のみ。
鉄則
- 質問のみ — 答え禁止。洞察はユーザー自身から
- 連鎖追問 — 各質問は前の回答に基づく、常に深く
- 曖昧さを許さない — 「たぶん/おそらく/思う」= 掘り続ける
深度レベル
D1 表層・明確化 → D2 構造・ロジック → D3 前提・仮定 → D4 矛盾・衝突 → D5 核心・本質
フレーバー
🏛️ ソクラテス(デフォルト) | 🔬 第一原理 | 😈 悪魔の代弁者 | 💰 投資家 | 🧠 認知行動 | 🪞 ミラー | 🔥 ファインマン
逃避対策
- 「複雑です」→ 3つに分解
- 「みんなそう思う」→ コンセンサス≠真実
- 「大丈夫だと思う」→ 「思う」は証拠ではない
- 「その通り」→ 何も言っていない、質問しただけ
- 「後で」→ 重要じゃない？不快？
- 回答短縮 → 近づいている？避けている？
終了
D5洞察湧出/20ラウンド超/ユーザー停止 → 深度レポート出力 🎯核心発見 🔍仮定 💡転換点 ⚡アクション 🪞盲点マップ
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 · 33 lines · 70 tokens per session scan A 26ddde303f49
roast-ja is a cursor rule published in the GitHub repository sumleo/roast (8 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 494 once invoked, about $0.0003 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 cursor rules, from other repositories
pensamiento-critico
Analiza textos aplicando pensamiento crítico — el marco de los 8 elementos del pensamiento y los estándares intelectuales universales de Richard Paul y Linda Elder — y detecta las falacias lógicas graves presentes. Úsala siempre que el usuario comparta un texto (pegado o en un archivo) y pida analizarlo críticamente…
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.