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 curlymolelabs/supericons --skill supericons-icon-searchgit clone --depth 1 https://github.com/curlymolelabs/supericonsWrote 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/curlymolelabs/supericons/supericons-icon-search)<a href="https://agentmods.dev/skills/curlymolelabs/supericons/supericons-icon-search"><img src="https://agentmods.dev/badge/skills/curlymolelabs/supericons/supericons-icon-search/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/curlymolelabs/supericons/supericons-icon-search"><img src="https://agentmods.dev/badge/skills/curlymolelabs/supericons/supericons-icon-search.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 | $0.00030 | $0.00357 |
| Opus 5 | $0.00015 | $0.00179 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
supericons-icon-search 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.
What it actually says
Supericons Icon Search
Use Supericons when the user asks for icons by meaning, feature, UI slot, product area, or visual style.
Best tool choices
- Use
search_iconswhen the user gives one concept, such as "database", "profile", "settings", "chill", or "AI model". - Use
recommend_iconswhen the user lists several UI slots, such as app tabs, sidebar items, dashboard panels, or feature names. - Use
get_iconwhen the user already knows the exact icon id and library. - Use
preview_iconsto refine a result set or visually compare known icon references. Usesearch_iconsfirst for a normal icon request. - Use
list_librarieswhen the user asks what icon libraries are available.
Response style
Show the icon id, library, and a short reason. Include SVG only when the user asks for it or needs code to paste into a project. When the tool returns a preview image or Markdown image, show it so the user can compare the choices. If no icons are found, say so and follow the tool's suggested next step. Never invent an icon.
Example prompts
Use Supericons to find a Lucide database icon. Show the icon id, library, and SVG.
Use Supericons to recommend icons for an AI dashboard sidebar: model, prompt, dataset, evaluation, deployment, and monitoring.
Use Supericons to preview the strongest camera scan icons so I can compare them visually.
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 · 35 lines · 30 tokens per session scan A 08f7f80704ba
supericons-icon-search is a skill published in the GitHub repository curlymolelabs/supericons (1 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 357 once invoked, about $0.0002 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
brand-guidelines-builder
Help non-designers evaluate work against brand guidelines and know what to fix.
brand-visual-quality
A quality-review workflow for brand visual assets such as logos, icons, theme variants, small-size optical adjustments, and monochrome masters.
design-system-architecture
A guide for turning a brand’s visual rules into a reusable design system. Design tokens are shared values such as colours, spacing, and font sizes; components are reusable interface building blocks.
ux-interaction-architecture
A UX design skill for planning how people move through screens, tasks, and interface states.
Accessibility Audit Helper
Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.
Form UX Optimizer
Reviews web forms for usability issues — field ordering, validation messages, error states, and accessibility.