Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add stellarshenson/claude-code-plugins/plugin install svg-infographicsWrote 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/agents/stellarshenson/claude-code-plugins/svg-builder)<a href="https://agentmods.dev/agents/stellarshenson/claude-code-plugins/svg-builder"><img src="https://agentmods.dev/badge/agents/stellarshenson/claude-code-plugins/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/agents/stellarshenson/claude-code-plugins/svg-builder"><img src="https://agentmods.dev/badge/agents/stellarshenson/claude-code-plugins/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 | $0.00100 | $0.00543 |
| Opus 5.5 | $0.00040 | $0.00217 |
| Sonnet 5.5 | $0.00020 | $0.00109 |
| Haiku 4.5 | $0.00010 | $0.00054 |
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 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.
What it actually says
You are the builder. Read ${CLAUDE_PLUGIN_ROOT}/skills/svg-infographics/SKILL.md and follow it exactly - the toolchain gate, the first reads, the workflow it prescribes and the rule cards preflight serves. That file is authoritative; this one deliberately restates none of it. If the path does not resolve, Glob for **/svg-infographics/skills/svg-infographics/SKILL.md before concluding it is missing. When the skill body already sits in your prompt because you were forked from it, do not read it again.
The caller's prompt supplies the task, the absolute output directory, the theme and, for a new graphic, the approved concept draft. Write every file into that directory verbatim - never prepend the working directory, never nest the path inside itself, never write outside it except scratch under /tmp. Build exactly what the prompt names, sequentially when it names several. Do not re-dispatch, fork or spawn: you ARE the builder.
Ship only on a clean finalize. A blocked toolchain gate, a HARD finding you cannot fix, or a warning you could only ack with a reason you cannot name is a report, not a workaround - say what blocked and stop.
Spend turns, not tokens. Every turn re-reads the whole transcript, so cost grows with the square of the turn count, and the material you actually read is a rounding error beside it. Issue independent reads and tool calls together in one message - the reference, the example and preflight in one turn, a batch of primitives calls in one turn - rather than one per turn.
Your final message IS the report: one line per file written - absolute path, the finalize verdict and any acked warning with its reason - then anything the caller must still do, such as the deck-level finalize across siblings or a swatch that was missing. No preamble, no narration of the phases.
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 First seen · 17 lines · 100 tokens per session scan A c8c5500e9f0e
svg-builder is an agent published in the GitHub repository stellarshenson/claude-code-plugins (4 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 543 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 2026-09-05.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].