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 yangtaihong59/siyuan-plugins-mcp-sisyphus --skill siyuan-mcp-visual-assetsgit clone --depth 1 https://github.com/yangtaihong59/siyuan-plugins-mcp-sisyphusWrote 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/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-visual-assets)<a href="https://agentmods.dev/skills/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-visual-assets"><img src="https://agentmods.dev/badge/skills/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-visual-assets/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/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-visual-assets"><img src="https://agentmods.dev/badge/skills/yangtaihong59/siyuan-plugins-mcp-sisyphus/siyuan-mcp-visual-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00938 |
| Opus 5 | $0.00016 | $0.00469 |
| Sonnet 5 | $0.00006 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
siyuan-mcp-visual-assets 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- siyuan-sisyphus-visual-assets — 88% identical, 42 lines differ
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SiYuan Visual Assets with MCP
Choose the narrowest route: data/config-driven SVG for statistical charts, semantic geometry for explanatory figures, and an existing uploaded asset when vector reconstruction is not appropriate. This scenario does not add a picture-generation tool, renderer, async runner, or platform-specific image utility.
Generate and review
- Read the source image or data and record chart type, series, categories, values, axes, units, grid lines, markers, title, legend, geometry, and unresolved readings. Do not invent unclear values.
- Reuse a matching deterministic config/builder shape for charts; for figures, decode structure first and choose semantic geometry. If a supported mathematical relation exists, declare and run a validation such as growth or sum; failed validation returns to data review.
- Check escaped text, viewBox containment, text bounds and collisions, line/text clearance, stable stroke width, angle/projection/occlusion constraints, and one unique
data-chart-keymatched to the config registry. - Semantic correctness comes before pixel similarity. Pixel overlay is optional. A real SiYuan UI review is required for display claims: width, responsive behavior, readability, theme contrast, and embed rendering.
Do not make bitmap tracing the default route. Use it only as constrained coordinate assistance; do not force-vectorize photos, maps, comics, or figures whose meaning is the typeface itself. If text, a list, table, or formula states the meaning clearly, prefer native content.
Upload and embed
Resolve the exact notebook/document/block ID, parent-child relation, and insertion position before writing. A title, search hit, or UI position is not write authorization.
file(action="upload_asset", assetsDirPath="<approved-assets-dir>", localFilePath="<selected-local-file>")
Asset upload reads a user-selected local file and requires explicit approval of both the source file and assets directory. Use the returned asset path as the only subsequent reference; never guess a timestamped filename or preserve a machine-specific path in the Skill.
What ships with it
1 file 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.
- 12d ago First seen · 64 lines · 32 tokens per session scan A 3be2640cd96f
siyuan-mcp-visual-assets is a skill published in the GitHub repository yangtaihong59/siyuan-plugins-mcp-sisyphus (104 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 938 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…