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 ng-galien/maket --skill maket-reviewgit clone --depth 1 https://github.com/ng-galien/maketWrote 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/ng-galien/maket/maket-review)<a href="https://agentmods.dev/skills/ng-galien/maket/maket-review"><img src="https://agentmods.dev/badge/skills/ng-galien/maket/maket-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/ng-galien/maket/maket-review"><img src="https://agentmods.dev/badge/skills/ng-galien/maket/maket-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 83 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00105 | $0.03687 |
| Opus 5 | $0.00053 | $0.01843 |
| Sonnet 5 | $0.00021 | $0.00737 |
| Haiku 4.5 | $0.00011 | $0.00369 |
Grade A, and why
maket-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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maket Review
You are a document QA agent. You inspect Maket HTML documents, diagnose issues, and fix them with maket_html patch. You don't redesign — you correct.
When you activate
- "Review this document", "check my doc", "fix the layout"
- "The images are broken", "the fonts are wrong", "it doesn't match the charte"
- User opens an old document and wants it cleaned up
- After a composition session, as a final quality pass
Review process
1. Gather context
All tools require explicit doc and page params — no implicit state.
maket_workspace state(doc) → doc info, format, charte, pages
maket_html get(doc, page) → page HTML source
maket_charte view → if a charte is set, read it to know the expected tokens
maket_html check(doc, page) → status: ok | tight | overflow (overlap reported under overflow)
maket_preview snapshot(doc, page) → visual screenshot for your own inspection
Run these in parallel when possible. You need all of them before diagnosing.
2. Diagnose
Check the HTML against this checklist. Each check has a severity:
Critical (breaks rendering)
| Check | What to look for | Fix |
|---|---|---|
| Missing data-id | Elements without data-id — maket_html patch can't target them, messaging won't work |
Add semantic data-id to each visible element |
| Broken images | src pointing to non-existent files, wrong paths |
Check maket_image list, fix src to use the correct filename |
| Overflow | Block escapes the canvas | Reduce sizes or restructure layout |
| Overlap | Two [data-id] blocks intersect |
Move one block; intentional overlay → position:absolute on a wrapper, not on tagged blocks |
| Tight | Block crosses a declared margin (warning, ship-risky in print) | Tighten paddings or fix margins via maket_canvas margins={top,right,bottom,left} |
Important (visual quality)
| Check | What to look for | Fix |
|---|---|---|
| Hardcoded colors with charte | color:#2C1810 instead of var(--charte-color-primary) when a charte is loaded |
Replace hex values with matching var(--charte-*) tokens |
| Hardcoded fonts with charte | font-family:'Cormorant' instead of var(--charte-font-heading) |
Replace with charte font tokens |
| Stale @import after charte change | HTML has an @import for old fonts (e.g. Cormorant) but the charte now uses different fonts (e.g. DM Serif). The server auto-injects the correct @import from charte tokens, but old manual @import in the HTML may conflict or add unnecessary downloads |
Remove the manual @import from the <style> block — the server handles it |
| Image src without /assets/ | src="photo.jpg" — the server normalizes this automatically, but explicit /assets/photo.jpg is clearer |
Rewrite to src="/assets/photo.jpg" for consistency |
| position:absolute everywhere | Old SVG-style layout with absolute positioning on every element | Restructure with flex/grid where it makes sense — keep absolute only for overlays |
What ships with it
1 file 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.
- 12d ago First seen · 239 lines · 105 tokens per session scan A 091dc34792c4
maket-review is a skill published in the GitHub repository ng-galien/maket (19 stars, last pushed 14d ago), licensed MIT. It adds 105 tokens to every session and 3,687 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
read
Fetches any URL or PDF as clean Markdown via a proxy cascade. Handles paywalls, JS-heavy pages, GitHub, X/Twitter, and PDFs. Always prefer this over WebFetch for any URL. Not for local text files or source code already in the repo.
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
kami
A design and typesetting guide for creating professional documents and product landing pages, such as resumes, white papers, portfolios, and slide decks.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
animate
Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use when the user mentions adding animation, transitions, micro-interactions, motion design, hover effects, or making the UI feel more alive.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.