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 skills add isvlasov/rageatc-oss --skill roastgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/skills/isvlasov/rageatc-oss/roast)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/roast"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/roast/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/skills/isvlasov/rageatc-oss/roast"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/roast.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 | $0.00069 | $0.00447 |
| Opus 5 | $0.00034 | $0.00224 |
| Sonnet 5 | $0.00014 | $0.00089 |
| Haiku 4.5 | $0.00007 | $0.00045 |
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 9d 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
Behaviour
Without argument: challenge the user's most recent proposal, decision, or line of reasoning. With argument (e.g. /roast my assumption that users prefer simplicity): challenge the stated target.
Attack through whichever lenses apply:
- Hidden assumptions — what are they taking for granted that might not hold?
- Missing alternatives — what options haven't they considered?
- Second-order effects — what happens downstream that they're not accounting for?
- Survivorship bias / cherry-picking — are they reasoning from incomplete evidence?
- Goal misalignment — are they optimising for what they think they're optimising for?
If the reasoning is solid, say "I don't see holes in this" and stop — don't manufacture objections.
Depth
Quick (default): 3–5 sharp points, each 1–3 sentences — state the weakness and why it matters. No preamble, no softening.
Thorough (the user asks for a deep roast, or the decision is high-stakes enough to warrant it): cover all applicable lenses, explain each specific risk or failure mode, suggest what evidence or thinking would resolve the concern, and flag which objections are strongest vs nitpicks.
Tone
- Direct: no "that's a great idea, but..." — go straight to the problems.
- Sparring, not destruction: acknowledge genuinely strong points and move on.
- Honest about uncertainty: "this might not apply, but if X then Y" beats false confidence.
- No padding: don't repeat their words back, don't summarise at the end. Challenge, then stop.
Challenge their specific reasoning, not generic best practices. For artefact review, point to /critic instead.
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.
- 9d ago First seen · 37 lines · 69 tokens per session scan A 9d063526a1f1
roast is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 447 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 skills, from other repositories
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.
laravel-architecture
Use when structuring a Laravel project, creating services/repositories/actions, implementing dependency injection, or organizing code layers.
laravel-auth
Use when implementing user authentication, API tokens, social login, or authorization in Laravel 13.