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 tetracoralla/armorial --skill icon-svg-selectgit clone --depth 1 https://github.com/tetracoralla/armorialWrote 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/tetracoralla/armorial/icon-svg-select)<a href="https://agentmods.dev/skills/tetracoralla/armorial/icon-svg-select"><img src="https://agentmods.dev/badge/skills/tetracoralla/armorial/icon-svg-select/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/tetracoralla/armorial/icon-svg-select"><img src="https://agentmods.dev/badge/skills/tetracoralla/armorial/icon-svg-select.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 | $0.00051 | $0.00779 |
| Opus 5.5 | $0.00020 | $0.00312 |
| Sonnet 5.5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
icon-svg-select 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Armorial
Use Armorial when a UI task needs existing icons and IconPark fits the project. The user need not name the tool. Preserve an established project icon system or an explicit visual requirement; do not replace it just to use Armorial.
Choose the metaphor from the action and surrounding interface. For example, renewal could use refresh, and a membership benefit could use crown or star. You can compare appearance and choose among candidates using your judgment. An ambiguous result means the deterministic matcher has not chosen; it does not prevent you from choosing an id. Ask the human when their preference would materially change the result, or open the picker when visual comparison helps.
Select and deliver
| Need | Available route |
|---|---|
| One or several meanings, before rendering | select_icons({intents:["search","settings"]}) returns ordered ids, policy, and unresolved candidates without SVG. |
| One meaning and its SVG | resolve_icon({intent:"search"}) includes the rendered asset. |
| Explore a meaning or visual alternative | search_icons({query:"notification"}), then choose an id. |
| Render chosen ids | get_icon({id:"icon-park:search"}) or get_icons({ids:[...]}) (up to 8 SVGs). |
| Human comparison | choose_icon({intent:"notification"}) opens the workbench. Only an explicit selection message supplies the human's choice. |
For partial selection, keep the successful mappings and work on the unresolved entries. Refine a meaning, compare candidates, or choose an exact id as needed. Batch related work when useful; call counts are an optimization, not a limit on investigation. Render through Armorial to preserve provider geometry and style; consumer markup, accessibility, layout, and visual judgment remain your work.
Pass a known configured context key, or omit it. Explicit appearance changes
use typed render settings, not edits to returned SVG paths. The response reports
the effective policy and any override. Inspect generated assets when debugging
requires it; avoid bringing large geometry dumps into context unnecessarily.
What ships with it
3 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.
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 Changed · -50 lines · -9 tokens per session aaa4c48180f2
- 2mo ago Changed · +71 lines a0d3f025150a
- 2mo ago First seen · 44 lines · 60 tokens per session scan A 3b16b6e56b30
icon-svg-select is a skill published in the GitHub repository tetracoralla/armorial (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 779 once invoked, about $0.0002 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.
icon-svg-select compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| icon-svg-selecttetracoralla/armorial | Skill | 0 | 4d ago | Apache-2.0 | A | 51 | Codex |
| codex-workspace-enhancerpapperrollinggery/codex-workspace-enhancer | Skill | 1 | 4d ago | MIT | A | 88 | Codex |
| visual-workspacepapperrollinggery/codex-workspace-enhancer | Skill | 1 | 4d ago | MIT | A | 51 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| architecture-diagrammateaix/mateclaw | Skill | 1.2k | 3d ago | Apache-2.0 | A | 15 | Claude Code, Codex |
| starcat-ui-prototypestarcat-app/Starcat | Skill | 215 | yesterday | MIT | A | 85 | Claude Code, Codex |
| component-family-consistencydembrandt/dembrandt-skills | Skill | 185 | 7d ago | MIT | A | 38 | Claude Code |