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 nguyenvanphituoc/shapeup-sdlc-plugin --skill svg-buildergit clone --depth 1 https://github.com/nguyenvanphituoc/shapeup-sdlc-pluginWrote 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/nguyenvanphituoc/shapeup-sdlc-plugin/svg-builder)<a href="https://agentmods.dev/skills/nguyenvanphituoc/shapeup-sdlc-plugin/svg-builder"><img src="https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/svg-builder/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/nguyenvanphituoc/shapeup-sdlc-plugin/svg-builder"><img src="https://agentmods.dev/badge/skills/nguyenvanphituoc/shapeup-sdlc-plugin/svg-builder.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 | $0.00212 | $0.03605 |
| Opus 5 | $0.00106 | $0.01802 |
| Sonnet 5 | $0.00042 | $0.00721 |
| Haiku 4.5 | $0.00021 | $0.00361 |
Grade A, and why
svg-builder 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 9d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SVG Builder
Turn a description into one valid, self-contained SVG.
The failure mode here is never ugliness — it is overlap. Text spilling past its box, an arrow slashing through an unrelated node, content clipped by a too-short viewBox. This happens because coordinates get invented token-by-token with no global view of the canvas. Every step below exists to prevent that, and the order matters: arithmetic first, markup second, motion third, validator fourth.
Workflow
- Intake — resolve the five slots below. Ask at most two questions.
- Route — pick the form from the user's verb, not their noun.
- Ledger — write the coordinate table in plain text. Do not skip this.
- Build — emit the markup, following the ledger.
- Animate — give the diagram the motion its behavior calls for. Not optional.
- Validate — run
scripts/check_svg.py. Fix what it reports. Re-run.
1. Intake
| Slot | Question | Default if unstated |
|---|---|---|
| Subject | What entities, and how do they relate? | — must be stated |
| Intent | Reference, intuition, data, or decorative? | Infer from the verb (§2) |
| Medium | Does it need playback controls? | Animated (§5); interactive only on request |
| Surface | Target width? Light, dark, or both? | 680px, both modes |
| Constraints | Brand palette, fonts, no-JS, size budget? | None |
Infer silently wherever the input implies an answer. Ask only when a wrong guess wastes the entire render — an ambiguous subject qualifies, an unstated width does not.
When the input is over budget: six or more entities in one diagram produces overlapping boxes and arrows through text, every time. Split into a sparse overview plus one detail SVG per sub-flow, and tell the user that is what you are doing. Several correct diagrams beat one crowded one.
2. Route on the verb, not the noun
The same subject wants a different picture depending on what was asked. "Transformer architecture" wants labelled boxes; "how does attention work" wants a fan of weight-scaled lines. Getting this wrong produces a technically valid diagram that answers a question nobody asked.
What ships with it
6 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.
- 9d ago First seen · 260 lines · 212 tokens per session scan A b1d6ac19341d
svg-builder is a skill published in the GitHub repository nguyenvanphituoc/shapeup-sdlc-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 212 tokens to every session and 3,605 once invoked, about $0.0011 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
artistic
High-contrast, expressive style with creative typography and bold color choices for visually striking interfaces.
from-intake
A workflow for reviewing material brought from another workspace and carrying relevant brand evidence into the project's assets. It checks inventories, brand guides, logos, and image sources before anything is used.
figma-use-slides
This skill helps agents use Figma's usefigma MCP tool in the Slides context. Can be used alongside figma-use which has foundational context for using the usefigma tool.
sidesight
Use SideSight for screenshots, images, error screenshots, UI mockups, architecture diagrams, charts, OCR, visual comparison, and videos when the host coding model is text-only. Route each visual task to the matching npx sidesight CLI command.
dynamic-archify
Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG / GIF / WebM. Accepts plain-language descriptions or pasted…
infographic-generator
An image-making workflow that turns a writing topic and outline into HTML pages and PNG screenshots. It includes four visual styles for different kinds of content.