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 agentmods add skills/vinsonconsulting/limner/vectorizenpx skills add vinsonconsulting/limner --skill vectorizegit clone --depth 1 https://github.com/vinsonconsulting/limnerWhat 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 | $0.00049 | $0.00811 |
| Opus 5 | $0.00024 | $0.00405 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
vectorize 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vectorize a raster image
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Use this skill to trace a raster image into a scalable SVG, so a logo, icon, or flat illustration stays crisp at any size and is editable in a vector tool. The limner_vectorize tool does the trace; it is a paid Recraft call. The reference at the end states when a vector beats a raster.
Procedure
- Check the source suits vectorizing. Flat graphics (logos, icons, line art) trace cleanly; photographs and shaded images do not.
- Vectorize. Call limner_vectorize with the source image URL. It is a paid Recraft call that returns an SVG through its capability URL.
- Refine if needed. Open the SVG in a vector editor (Inkscape, Affinity Designer) for path cleanup, or use it directly where scalability matters.
- Rasterize back if a fixed-size raster is needed. Render the SVG out through compose.
Judgment
- Vectorize flat art, not photos. A traced photograph is a heavy, messy SVG; upscale a photo instead.
- When you control the source, generate vector from the start with Recraft rather than tracing a raster afterward.
- It is a paid call, so vectorize the final raster, not every draft.
Reference
The text below is generated from the Limner guidance core (@limner/core), the
same source the MCP vectorize prompt serves, so this skill and that prompt cannot
drift. Do not edit the generated region by hand; run
pnpm --filter @limner/limner-agent gen:skills instead.
Vectorize a raster image
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Vectorizing traces a raster image (a PNG or JPEG) into a scalable SVG made of paths, so a logo, icon, or flat illustration stays crisp at any size and can be edited in a vector tool. Limner does this with the limner_vectorize tool, a paid Recraft call: it takes a source image by URL and returns an SVG.
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.
- yesterday First seen · 66 lines · 49 tokens per session scan A 8559c054073d
vectorize is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 20d ago), licensed Apache-2.0. It adds 49 tokens to every session and 811 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 2026-08-31.
Other skills, from other repositories
flux-3-product-ads
Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.
bfl-api
BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.
flux-3-archival-formats
Use when a FLUX 3 video needs a period or archival look. Covers naming a recording format instead of a mood, per-format artifacts, and templates.
flux-3-keyframes-continuation
Use when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v).
flux-3-prompt-doctor
Use when diagnosing a FLUX 3 brief before generation. Resolve missing, conflicting, or schema-changing requirements.
flux-image-best-practices
Comprehensive guide for BFL FLUX image generation models. Covers prompting, T2I, I2I, structured JSON, hex colors, typography, multi-reference editing, and model-specific best practices for FLUX.2 and FLUX.1 families.