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/file-typesnpx skills add vinsonconsulting/limner --skill file-typesgit clone --depth 1 https://github.com/vinsonconsulting/limnerWrote 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/vinsonconsulting/limner/file-types)<a href="https://agentmods.dev/skills/vinsonconsulting/limner/file-types"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/file-types.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00569 |
| Opus 5 | $0.00024 | $0.00284 |
| Sonnet 5 | $0.00010 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
file-types 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 3d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File types
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
A quick reference for the image and document formats Limner reads and writes. Use it when deciding which format to generate or convert to.
The matrix below is generated from the Limner guidance core (@limner/core),
the same source the MCP limner://reference/file-types resource serves, so this
skill and that resource cannot drift. Do not edit the generated region by
hand; run pnpm --filter @limner/limner-agent gen:skills instead.
Image & document file types
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Choosing an output format trades fidelity against size, transparency, and downstream tooling. This matrix covers the raster, vector, and document formats Limner handles.
| Format | Compression | Alpha | Color model | Typical use |
|---|---|---|---|---|
| PNG | Lossless | Yes | RGB / RGBA | UI assets, screenshots, line art (crisp edges or transparency) |
| JPEG | Lossy | No | RGB / CMYK | Photographs where small size beats pixel-exactness |
| WebP | Lossy or lossless | Yes | RGB / RGBA | Web delivery (smaller than PNG/JPEG at similar quality) |
| AVIF | Lossy or lossless | Yes | RGB / RGBA | Next-gen web delivery (best compression, newer decoder support) |
| SVG | Lossless (vector) | Yes | RGB | Icons, logos, diagrams (resolution-independent markup) |
| TIFF | Lossless or lossy | Yes | RGB / CMYK / grayscale | Print and archival masters; high bit-depth, CMYK separations |
| Mixed (container) | Yes | RGB / CMYK / grayscale | Multi-page, print-ready output: vector + raster + text |
- Lossless (PNG, SVG, TIFF) preserves every pixel or path; lossy (JPEG) discards detail for size.
- Alpha/transparency is available everywhere except baseline JPEG.
- CMYK matters for print (JPEG, TIFF, PDF); the web formats are RGB only.
- Raster DPI is intrinsic to the pixel grid; SVG and PDF scale without DPI loss.
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.
- 3d ago First seen · 42 lines · 48 tokens per session scan A 6c95a281dead
file-types is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 48 tokens to every session and 569 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.
aatmf-t08-deception
AATMF T8 — External Deception & Misinformation. Misinfo generation at scale, persona impersonation, document fabrication, hallucination weaponization.
guizang-ppt-skill
生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、演讲者视图、观众屏同步、讲稿备注、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT，或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。.
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).