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 smixs/disruptor-skills --skill unvibe-reviewgit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/unvibe-review)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/unvibe-review"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/unvibe-review/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/smixs/disruptor-skills/unvibe-review"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/unvibe-review.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 | $0.00092 | $0.03310 |
| Opus 5 | $0.00046 | $0.01655 |
| Sonnet 5 | $0.00018 | $0.00662 |
| Haiku 4.5 | $0.00009 | $0.00331 |
Grade A, and why
unvibe-review 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 12d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unvibe-review
Stage contract
- Stage: 5b. Cut (inside the build loop) · Kind: method
- Inputs: an artifact the review-and-fix ratchet has been growing.
- Outputs: ranked reframes/cuts by collapse-power × confidence, each steelmanned, plus a calibrate step.
- Entry gate: ~1 cut pass per ~5 review iterations — or sooner if several rounds only ever added.
- Done when: the cut pass returns its seeds; then polish-to-settle on the touched area before moving on.
- Next: back to the
converging-and-polishingskill.
Overview
"Vibecode" names an artifact that technically solves every problem but is bloated, inelegant, and fragile — every piece added because it felt necessary, the sum a tangle no one can hold in their head. "Unvibe" is the review that finds that bloat and, more importantly, the simplifying reframe that dissolves a whole class of it at once.
Core principle: "works" ≠ "good." Complexity each step justified locally is still bloat globally. The cure is rarely another patch — it is a reframe that makes a dozen pieces unnecessary at once.
The one insight that matters most (read this even if you read nothing else): Any iterate-until-no-complaints loop is a one-way ratchet. A reviewer, editor, or stakeholder who "fails the work if they find nothing to fix" must always find something to add. Rounds add sections, caveats, checks, characters, effects, mechanisms, frameworks; rounds almost never remove. With only a "make it correct / complete" force and no "make it minimal" force, the work grows monotonically — which is exactly how bloat accretes while everyone behaves reasonably. This skill is the missing counter-force: a pass whose only job is to delete, unify, and reframe.
When to use
- After many rounds of review/iteration/feedback (the ratchet has been running).
- When you suspect over-engineering but "every part seems necessary."
- When inheriting something that feels heavier than the job it does.
- Any domain: code, prose/books, research & analysis, video/audio editing, ops/process, slide decks, org design, product specs.
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.
- 12d ago First seen · 216 lines · 92 tokens per session scan A e57cbf444a73
unvibe-review is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 3,310 once invoked, about $0.0005 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.
Other skills, from other repositories
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
check
Confirm a change before merge. /check verify drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). /check review runs a senior code review on a fresh model, one that did not write the code. Verify after /develop, review before a PR. Writes to docs/reviews/, never…
reflecting-findings
Use when a reflection package hands you another agent's review findings to verify (before they become a fix request): you are the REFLECTOR, an independent skeptic. Judge each finding against the real code and settle it with reflectfinding — kept or refuted.
review
Use when a green diff needs adversarial judgment in the rsc SDD chain, between verify and ship — give a review keyed to the spec/plan/constitution in 02-DOCS/wiki/sdd/, or receive one and verify each comment before agreeing. NOT running lint/type/tests (that is verify), NOT the spec-less standalone pass (that is…
code-review
Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…
demand-elegance
Challenges hacky fixes on non-trivial changes.