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 vria-consulting/vria-fire-detect --skill handoffgit clone --depth 1 https://github.com/vria-consulting/vria-fire-detectWrote 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/vria-consulting/vria-fire-detect/handoff)<a href="https://agentmods.dev/skills/vria-consulting/vria-fire-detect/handoff"><img src="https://agentmods.dev/badge/skills/vria-consulting/vria-fire-detect/handoff/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/vria-consulting/vria-fire-detect/handoff"><img src="https://agentmods.dev/badge/skills/vria-consulting/vria-fire-detect/handoff.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 | $0.00068 | $0.00310 |
| Opus 5 | $0.00034 | $0.00155 |
| Sonnet 5 | $0.00014 | $0.00062 |
| Haiku 4.5 | $0.00007 | $0.00031 |
Grade A, and why
kanari-design 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 8d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
53 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.
- assets/favicon.svg 457 B
- assets/logo-mono-blanc.svg 725 B
- assets/logo-mono-jaune-anime.svg 725 B
- assets/logo-mono-jaune.svg 725 B
- assets/logo-mono-noir.svg 725 B
- assets/logo-symbole-anime.svg 631 B
- assets/logo-symbole.svg 631 B
- components/buttons/Button.d.ts 569 B runs code
- components/buttons/Button.jsx 1.6 KB
- components/buttons/Button.prompt.md 522 B
- components/buttons/buttons.card.html 2.3 KB
- components/buttons/IconButton.d.ts 436 B runs code
- components/buttons/IconButton.jsx 836 B
- components/buttons/IconButton.prompt.md 233 B
- components/display/Badge.d.ts 401 B runs code
- components/display/Badge.jsx 1.0 KB
- components/display/Badge.prompt.md 192 B
- components/display/Card.d.ts 399 B runs code
- components/display/Card.jsx 792 B
- components/display/Card.prompt.md 144 B
- components/display/display.card.html 2.1 KB
- components/feedback/Alert.d.ts 466 B runs code
- components/feedback/Alert.jsx 1.2 KB
- components/feedback/Alert.prompt.md 350 B
- components/feedback/feedback.card.html 1.6 KB
- components/feedback/Toast.d.ts 263 B runs code
- components/feedback/Toast.jsx 1.0 KB
- components/feedback/Toast.prompt.md 183 B
- components/forms/Checkbox.d.ts 272 B runs code
- components/forms/Checkbox.jsx 1.0 KB
- components/forms/Checkbox.prompt.md 135 B
- components/forms/forms.card.html 2.6 KB
- components/forms/Input.d.ts 411 B runs code
- components/forms/Input.jsx 1.2 KB
- components/forms/Input.prompt.md 247 B
- components/forms/Switch.d.ts 273 B runs code
- components/forms/Switch.jsx 1.0 KB
- components/forms/Switch.prompt.md 158 B
- components/navigation/navigation.card.html 1.0 KB
- components/navigation/Tabs.d.ts 259 B runs code
- components/navigation/Tabs.jsx 964 B
- components/navigation/Tabs.prompt.md 149 B
- INSTRUCTIONS.md 3.5 KB
- maquette/Kanari App Redesign v2.dc.html 18 KB
- maquette/support.js 63 KB runs code
- readme.md 6.4 KB
- styles.css 128 B
- tokens/colors.css 1.5 KB
- tokens/fonts.css 294 B
- tokens/spacing.css 1.1 KB
- tokens/typography.css 1.2 KB
- ui_kits/website/index.html 6.5 KB
- ui_kits/website/README.md 357 B
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.
- 8d ago First seen · 12 lines · 68 tokens per session scan A 94c341ac531a
kanari-design is a skill published in the GitHub repository vria-consulting/vria-fire-detect (1 stars, last pushed yesterday), with no licence file. It adds 68 tokens to every session and 310 once invoked, about $0.0003 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
magic-ui
Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.
kiranism-shadcn-dashboard
Guide for building features, pages, tables, forms, themes, and navigation in this Next.js 16 shadcn dashboard template. Use this skill whenever the user wants to add a new page, create a feature module, build a data table, add a form, configure navigation items, add a theme, set up RBAC access control, or work with…
omd-apply
A skill that applies a project's DESIGN.md file as visual and brand guidance for interface work. It covers components, colors, fonts, layout, copy, motion, and visual assets.
favicon-icon-generator
Generate and validate favicon and application icon systems for web projects. Use when creating SVG icons, web manifests, framework metadata, or cross-platform favicon assets.
multi-surface-render
Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…
common-ui-design
Design distinctive, production-grade frontend UI with bold aesthetic choices. Use when building web components, pages, interfaces, dashboards, or applications in any framework (React, Next.js, Angular, Vue, HTML/CSS).