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/sumleo/roast/roastgit 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 | $0.00000 | $0.00033 |
| Opus 5 | $0.00000 | $0.00016 |
| Sonnet 5 | $0.00000 | $0.00007 |
| Haiku 4.5 | $0.00000 | $0.00003 |
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.
What it actually says
激活烤问模式。AI 将停止回答问题，开始向你提问——逐层深入，直到挖出你真正的想法。
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 · 2 lines · 0 tokens per session scan A 282b30d8dad0
roast is a command published in the GitHub repository sumleo/roast (8 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 33 tokens. 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 commands, from other repositories
go
Run all six lenses in parallel and synthesize the findings.
assume
Challenge the hidden assumptions in a document.
evidence
Examine the evidence and sources behind the claims.
meta
Question whether the document is asking the right question.
synth
Synthesize the lens evaluations in a directory into one summary.
method
Force methodology-driven analysis of a task, optionally with a specific method.