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 liustack/vibemaster --skill style-auditgit clone --depth 1 https://github.com/liustack/vibemasterWrote 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/liustack/vibemaster/style-audit)<a href="https://agentmods.dev/skills/liustack/vibemaster/style-audit"><img src="https://agentmods.dev/badge/skills/liustack/vibemaster/style-audit/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/liustack/vibemaster/style-audit"><img src="https://agentmods.dev/badge/skills/liustack/vibemaster/style-audit.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 | $0.00078 | $0.00578 |
| Opus 5.5 | $0.00031 | $0.00231 |
| Sonnet 5.5 | $0.00016 | $0.00116 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
style-audit 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 1mo 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
style-audit: expression-style audit for product texts
Project-local authoring tool. The shipped product lives in skills/ — this skill never ships with it.
Two layers, one ratchet
- This skill is the judgment layer: it finds what a script cannot — coined labels without an in-sentence explanation, loan-word nouns minted from foreign material, process traces in product copy.
scripts/check-style.shis the mechanical layer: a banned-term list plus a semicolon check, wired into CI. It only knows what audits have already found.- The ratchet: every term an audit purges gets appended to
BANNEDinscripts/check-style.sh, so it can never come back.
Disciplines to audit against
- Plain language (
rules/plain-language.md): everyday words over terminology — the test is whether a reader outside the project understands without looking anything up. Coined labels and metaphors must be explained in the same sentence on first use. Foreign material is described in your own words, not transliterated into a pet noun. - Punctuation (
rules/punctuation.md): no semicolons in prose. The script catches this — spot-check only. - Content discipline: no source citations in product copy (no "per X's book", no repo credits), no process traces ("changed because review said"), no invented metaphors.
Procedure
- Scope: changed files by default (
git diff --name-only), or all ofskills/,rules/,README*on request..zh-CNtranslations are held to the same bar. - Report each finding as: the term or sentence, a quoted line, why it fails (one clause), and a concrete fix — a plain rewrite or an in-sentence explanation, with exact wording.
- Err on the side of silence: report only what an outside reader would actually stumble on. Terms explained in place, industry-standard vocabulary (API, spec, TDD, AARRR), and skill or product names are not findings.
- After fixes land and a term is fully purged, append it to
BANNEDinscripts/check-style.sh— in both stacks if it appeared in both. - Run
bash scripts/check-style.shand confirm green before committing.
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.
- 1mo ago First seen · 29 lines · 78 tokens per session scan A 3610b76eb8b7
style-audit is a skill published in the GitHub repository liustack/vibemaster (13 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 578 once invoked, about $0.0003 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.