Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Kevin-Liu-01/Sigil-UInpx agentmods add skills/kevin-liu-01/sigil-ui/sigil-auditWrote 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/kevin-liu-01/sigil-ui/sigil-audit)<a href="https://agentmods.dev/skills/kevin-liu-01/sigil-ui/sigil-audit"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-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/kevin-liu-01/sigil-ui/sigil-audit"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/sigil-ui/sigil-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 | $0.00004 | $0.02013 |
| Opus 5 | $0.00002 | $0.01007 |
| Sonnet 5 | $0.00001 | $0.00403 |
| Haiku 4.5 | $0.00000 | $0.00201 |
Grade A, and why
sigil-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 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sigil Component Auditor
Browser + static auditor for every component preview page in the Sigil docs site, the /components landing showcase, and the showcase ↔ docs reconciliation.
Scripts
| Script | Purpose |
|---|---|
scripts/audit-components.mjs |
Crawls every /docs/components/<slug> page; checks runtime errors, hydration, token compliance, screenshots each preview block. |
scripts/audit-visual.mjs |
Per-doc visual quality scan — flags components rendering too narrow (cards < 240px, sections < 400px), extreme aspect ratios, or tiny dominant elements. Whitelists known-small (icons, badges) and known-tall (sidebars). |
scripts/audit-showcase.mjs |
Loads /components and clicks through every category tab; verifies each filter view hydrates and renders the expected cell count. |
scripts/audit-showcase-deep.mjs |
Loads /components "All" view; walks every cell's DOM looking for NaN, undefined, [object Object], or empty containers. Captures a full-page screenshot. |
scripts/audit-showcase-visual.mjs |
Per-cell visual scan across all 18 category tabs on /components; flags showcase cells whose card/section shrinks below 100px or 150px. |
scripts/validate-showcase-docs.mjs |
Static validator: every entry on the showcase resolves to either a real MDX file or an explicit docPath: null. Reports missing docs and duplicate names. |
scripts/improve-bare-demos.mjs |
Bulk-upgrades bare <X /> MDX previews to richer examples with realistic props. |
scripts/fix-broken-demos.mjs |
Targeted MDX rewrites for components with wrong prop names. |
scripts/fix-narrow-demos.mjs |
Bulk-applies <ComponentPreview vertical> + sized containers to demos that render too narrow. |
scripts/add-missing-previews.mjs |
Adds a ## Preview section to docs that have no <ComponentPreview> block at all. |
When to Use
- User asks for a "component audit", "QA pass", "audit all components", "check every preview"
- User reports a class of issues (e.g., "preview demos look broken", "components render with no data")
- After a token rename, preset rework, or large component-library refactor — verify nothing regressed visually
- Before a release — produce a clean baseline report
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 · 139 lines · 4 tokens per session scan A d582b2fadb61
sigil-audit is a skill published in the GitHub repository Kevin-Liu-01/Sigil-UI (9 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 2,013 once invoked, about $0.0000 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
webkit-ui-verify
Drive a finished @aziontech/webkit screen in a real browser (Playwright, headless Chromium) and OBSERVE before declaring it done — screenshot both themes at multiple widths, assert zero console errors, run axe-core against the live tree, and exercise the loading/empty/error states and the primary interaction. The…
diff
Scaffold a playwright visual regression test suite that takes per-route full-page screenshots and compares against committed baselines. Pixel diffing is done by playwright's toHaveScreenshot, not by dragoon. Use when the user wants visual regression coverage. Pass --routes to set the routes to capture. Defaults to…
webapp-testing
Test local web applications with Playwright. Use when asked to verify frontend functionality, debug UI behavior, capture browser screenshots, or inspect browser logs. Pure-methodology skill: teaches the reconnaissance-then-action pattern and decision tree for static vs dynamic apps, with no bundled scripts. The agent…
test-playable-web-games
Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.