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 | $0.00060 | $0.01506 |
| Opus 5 | $0.00030 | $0.00753 |
| Sonnet 5 | $0.00012 | $0.00301 |
| Haiku 4.5 | $0.00006 | $0.00151 |
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 7d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Armorial
Use Armorial as the only icon geometry and policy authority. Never redraw,
approximate, or silently edit returned paths. Use only the installed MCP tools
or the managed scripts/armorial launcher beside this Skill; never substitute a
source checkout, another icon corpus, or model-authored SVG.
Route the request
- For one ordinary meaning, call
resolve_icononce with a compact visible object or action. Do not forward a full business sentence. Its successful result already includes the asset; do not follow it withget_icon. - For two or more meanings when only canonical ids are needed, first decide
one compact visible meaning for every business label from its action and
context. For example, renewal may deliberately use
refresh; a membership benefit may deliberately usecrown,badge, orstar. That semantic choice remains Agent or human judgment. Then run exactly one installed CLI call:scripts/armorial batch <compact-intent...> --resolve-intents --format json. Use the ordered, indexeditemsmapping. Do not launch one resolver per intent. If any item is unresolved, keep every returned resolved mapping, search only the unresolved semantic axis, and issue at most one corrected batch. - For alternatives, call
search_iconswith one short catalog-facing term. ComparematchedOn; search a second axis only when object, action, or direction genuinely differs. Callget_icononly after an exact id is chosen. - For an already-known id, call
get_icon. For up to eight independent known ids, callget_iconsonce. For a larger or durable set, use the installed CLI batch route so SVG payloads do not enter model context. - Open
choose_icononly when the user asks to choose visually, rejects the prior choice, or taste is the remaining ambiguity. Stop after opening it and wait for its explicit selection message. - Before replacing several icons in an HTML artifact, read
references/html-retrofit.md.
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.
- 7d ago Changed · +71 lines a0d3f025150a
- 10d 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 yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 1,506 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
codex-workspace-enhancer
Audit, install, adapt, or extend Codex Workspace Enhancer. Prefer the native Codex plugin and fullscreen MCP App for a port-free visual asset canvas; use the legacy sidebar/AssetBrowser adapters only for features the plugin does not yet provide. Use for native Codex widgets, visual workspace UI, image canvases, task…
visual-workspace
Open and use the native Visual Workspace infinite canvas for the active Codex project. Use when the user asks for a canvas, moodboard, image board, asset browser, spatial image arrangement, or the Codex Workspace Enhancer UI.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
wireframe-annotated
An annotated / redline lo-fi wireframe — a desktop landing/marketing page drawn as flat greyboxes inside a browser chrome frame, overlaid with numbered annotation pins (①②③④⑤) in a single accent color, paired with a right-hand SPEC PANEL that lists each numbered pin with a short engineering / UX note. This is the…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.