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 ChanMeng666/svg-animation-studio --skill svg-verifygit clone --depth 1 https://github.com/ChanMeng666/svg-animation-studioWrote 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/chanmeng666/svg-animation-studio/svg-verify)<a href="https://agentmods.dev/skills/chanmeng666/svg-animation-studio/svg-verify"><img src="https://agentmods.dev/badge/skills/chanmeng666/svg-animation-studio/svg-verify/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/chanmeng666/svg-animation-studio/svg-verify"><img src="https://agentmods.dev/badge/skills/chanmeng666/svg-animation-studio/svg-verify.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 | $0.00105 | $0.01927 |
| Opus 5 | $0.00053 | $0.00963 |
| Sonnet 5 | $0.00021 | $0.00385 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
svg-verify scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Bash(npm run dev*), Bash(curl*), mcp__chrome-devtools__* How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You verify a generated SVG. You run in an isolated subagent context. The main thread does NOT see your screenshots or browser logs — only your final verdict. Keep that verdict ≤ 100 words. Brevity is the contract.
What was passed in
$ARGUMENTS is the preset slug (e.g., claude-jumping, or my-new-mascot).
If it's empty, return:
VERDICT: fail No slug provided. Usage:
/svg-verify <preset-slug>.
Workflow
1. Ensure preview server is up
Check if http://localhost:3030/api/presets responds:
curl -s -o /dev/null -w '%{http_code}' http://localhost:3030/api/presets
If not 200, start it in the background:
npm run dev &
Wait for "Ready" in the log (poll the log file with until grep -q "Ready").
If it doesn't come up in 30 s, return:
VERDICT: fail Could not start preview server. Check the npm run dev output.
2. Open the preset in Chrome
Use mcp__chrome-devtools__new_page to open
http://localhost:3030/api/svg?preset=$ARGUMENTS. The page renders the SVG
inline with the CSS animations running.
If the response is non-2xx or the rendered page shows an error message, return:
VERDICT: fail /api/svg returned or compose() threw: .
2b. If the SVG is for embedding (README / GitHub / <img>), ALSO verify in <img> mode
The /api/svg page renders the SVG inline, which is permissive: external
fonts load, scripts run, every CSS feature works. But the common destination —
a GitHub README or social card — embeds the file as <img src="...svg">, a
restricted image document that behaves differently. Inline-only verification
gives false passes. When the target is an embed, verify there too:
- Write a tiny same-origin host page next to the SVG and open it:
<body><img src="<slug>.svg" width="..."></body>(afile://HTML file referencing the SVG by relative path — do NOT usesetContentwith afile://src; the browser blocks that cross-origin and you'll see a broken image that is a test artifact, not a real failure). - Confirm the image actually decoded:
img.naturalWidth > 0. - Capture frames here too and check specifically for the
<img>-only failures:- Text renders in the wrong font → external fonts don't load in
<img>mode. The fix is to OUTLINE text to paths at build time (seedocs/embedding-animated-svg.md), not to rely onfont-family. - Nothing moves → the animation depends on JS (stripped in
<img>) instead of CSS@keyframes/ SMIL (both of which DO run in<img>mode).
- Text renders in the wrong font → external fonts don't load in
- For a one-shot reveal, reload before each timed screenshot so the animation restarts at t=0 (a reused page may have already settled).
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.
- 11d ago First seen · 204 lines · 105 tokens per session scan A 331a12b3b8be
svg-verify is a skill published in the GitHub repository ChanMeng666/svg-animation-studio (2 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,927 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
information-architecture
Design the structure of a website or product including sitemap, navigation, URL structure, content types, taxonomy, and labeling. Use this skill whenever the user asks to plan a sitemap, design navigation, structure URLs, define content types, build taxonomies, design site search, or organize content at the system…
journey-mapping
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the…
usability-testing
Plan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis. Use this skill whenever the user wants to test usability, run a moderated test, run an unmoderated test, validate a design, find usability issues, or improve task…
brand-style-guide
Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts. Use this skill whenever the user wants to create brand guidelines, document an existing brand, build a brand book, audit an existing style…
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.