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 takaoumehara/superforge-skill --skill superforge-roastgit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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/takaoumehara/superforge-skill/superforge-roast)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-roast"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-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/takaoumehara/superforge-skill/superforge-roast"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-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 | $0.00127 | $0.01293 |
| Opus 5 | $0.00063 | $0.00647 |
| Sonnet 5 | $0.00025 | $0.00259 |
| Haiku 4.5 | $0.00013 | $0.00129 |
Grade A, and why
superforge-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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge Roast — Uncompromising Critique Engine
Use this skill to subject designs, code, PRDs, copy, or architecture plans to a ruthless, zero-fluff critique. This engine strips away AI politeness, highlights hidden flaws, and forces radical polish before shipping.
1. Critique Mindset (Zero AI Compliments)
- Ban False Praise: Never open with "Great start!", "Looks awesome!", or polite agreement.
- Direct & Unsparing: Point out confusion, bad assumptions, ugly layout math, unnecessary complexity, or weak copy immediately.
- Constructive Solution: For every flaw roasted, specify the exact, actionable path to fix it.
2. Roast Dimensions
Analyze the artifact across 4 ruthless lenses:
- UX & Friction Roast:
- Where will a user get confused, annoyed, or abandon the flow?
- Are there hidden edge cases or missing error states?
- Design & Aesthetic Roast:
- Does it look like generic AI template code?
- Is the typography scale inconsistent? Are margins arbitrary?
- Architecture & Code Roast:
- Is there over-engineering or premature abstraction?
- Where will this break when data scales or network drops?
- Copy & Positioning Roast:
- Is the copy preachy, jargon-filled, or vague?
- Does it sound like corporate filler instead of direct human communication?
The lenses have to be independent, and in one context they are not
Running all four in a single pass is the compromised version of this skill. By the fourth lens the same context has already read the first three and agrees with them — the later critics inherit the earlier ones' framing, and a flaw that only shows up when you have not been told what to look for never surfaces. Worse, the pass that generates findings is also the pass that decides which ones are real, and it has no reason to kill its own.
Where Claude Code is available, run workflows/superforge-roast-council.js
instead: five critics on separate contexts that never see each other, then an
Opus skeptic per lens whose only job is to kill findings that turn out to be
absent, taste, already handled, or fixed at a cost higher than the defect. Then
one judge writes docs/critique.md. Eleven agents; say "use a workflow" or run
/superforge-roast-council.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 128 lines · 127 tokens per session scan A b534a8d4dc08
superforge-roast is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 24d ago), licensed MIT. It adds 127 tokens to every session and 1,293 once invoked, about $0.0006 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
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
adversarial-squad
Deploy a bounded, profile-loaded adversarial review squad at an SDD point-cut (post-spec, post-plan, post-tasks, pre-merge, or an ad-hoc decision) so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec…
ss-review
Review UI code for design system compliance, accessibility, and best practices.
resolve-pr-comments
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.