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/stephansama/packagesnpx agentmods add skills/stephansama/packages/astro-iconify-svgmapWrote 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/stephansama/packages/astro-iconify-svgmap)<a href="https://agentmods.dev/skills/stephansama/packages/astro-iconify-svgmap"><img src="https://agentmods.dev/badge/skills/stephansama/packages/astro-iconify-svgmap/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/stephansama/packages/astro-iconify-svgmap"><img src="https://agentmods.dev/badge/skills/stephansama/packages/astro-iconify-svgmap.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 | $0.00110 | $0.01578 |
| Opus 5.5 | $0.00044 | $0.00631 |
| Sonnet 5.5 | $0.00022 | $0.00316 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
astro-iconify-svgmap 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
astro-iconify-svgmap
Deprecated: use
@stephansama/vite-iconify-svgmapfor new projects. It keeps icon usage in memory instead of tracking files, supports staticimport href from "virtual:iconify-svgmap/<pack>/<icon>"imports, and writes sprites straight into the build output.
Generates SVG sprite maps from Iconify icon packs at build time and serves them during dev. Icons are registered lazily via getIcon() and assembled into per-pack sprite files.
Setup
- Install the integration and at least one
@iconify-json/*pack:
pnpm add @stephansama/astro-iconify-svgmap @iconify-json/mdi
- Add to
astro.config.mjs:
import { createIntegration } from "@stephansama/astro-iconify-svgmap";
import { defineConfig } from "astro/config";
export default defineConfig({
integrations: [createIntegration()],
});
- Import the virtual module in your base layout (this activates the Vite plugin):
---
// src/layouts/BaseLayout.astro
import "virtual:iconify-svgmap";
---
- Use icons in any
.astrocomponent:
---
import { getIcon } from "@stephansama/astro-iconify-svgmap/get";
const iconHref = await getIcon("mdi", "home");
---
<svg width="24" height="24">
<use href={iconHref}></use>
</svg>
Core Patterns
Basic icon rendering
---
import { getIcon } from "@stephansama/astro-iconify-svgmap/get";
const href = await getIcon("mdi", "account");
---
<svg width="24" height="24" aria-hidden="true">
<use href={href}></use>
</svg>
getIcon(pack, name) returns /<pack>.svg#<name> — a fragment reference into the generated sprite. On the server it also registers the icon in the usage tracking file so the build step knows to include it in the sprite.
Monorepo setup with iconifyRootDirectory
// astro.config.mjs — inside a pnpm monorepo where icons are in the workspace root
import { createIntegration } from "@stephansama/astro-iconify-svgmap";
import { defineConfig } from "astro/config";
export default defineConfig({
integrations: [
createIntegration({
iconifyRootDirectory: new URL("../../", import.meta.url),
}),
],
});
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 · +2 lines · +14 tokens per session 70a79dbb4cf0
- 2mo ago First seen · 217 lines · 96 tokens per session scan A edcfe1aaae20
astro-iconify-svgmap is a skill published in the GitHub repository stephansama/packages (5 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 1,578 once invoked, about $0.0004 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.
astro-iconify-svgmap compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| astro-iconify-svgmapstephansama/packages | Skill | 5 | 3d ago | MIT | A | 110 | Claude Code, Codex |
| opendia-harnessaeonfun/opendia | Skill | 1.9k | 4d ago | MIT | A | 52 | Claude Code |
| npm-securitybodadotsh/npm-security-best-practices | Skill | 858 | 5d ago | MIT | A | 43 | Claude Code, Codex |
| opendiaaeonfun/opendia | Skill | 1.9k | 4d ago | MIT | A | 66 | Claude Code |
| frontmcp-extensibilityagentfront/frontmcp | Skill | 153 | 5d ago | Apache-2.0 | A | 124 | Claude Code, Codex |
| glin-profanityglincker/glin-profanity | Skill | 70 | 4d ago | MIT | A | 62 | Claude Code, Codex |
| huly-clidearlordylord/huly-mcp | Skill | 64 | 6d ago | MIT | A | 56 | Codex |