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 danielrosehill/Claude-Image-Production-Plugin --skill fast-resizegit clone --depth 1 https://github.com/danielrosehill/Claude-Image-Production-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/danielrosehill/claude-image-production-plugin/fast-resize)<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/fast-resize"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/fast-resize/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/danielrosehill/claude-image-production-plugin/fast-resize"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/fast-resize.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 | $0.00074 | $0.00991 |
| Opus 5.5 | $0.00030 | $0.00396 |
| Sonnet 5.5 | $0.00015 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
fast-resize 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 2mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast Resize (libvips)
Batch image resize using libvips. Material throughput improvement over ImageMagick on large libraries — typical 5–10× speed-up and lower peak memory.
When to use
- Batch is >500 images.
- The user is feeling ImageMagick's slowness (or is about to).
- The job is "resize this directory" — pure resize without compositing or filters.
Do not use this skill for:
- Small batches (<100 images) —
batch-resizeis fine, no point swapping engines. - Resize-with-filter / resize-with-text / multi-op pipelines — ImageMagick is the better tool for compound work.
Inputs
- Input directory — required.
- Target size — one of:
--width N— resize so width = N, height auto.--height N— resize so height = N, width auto.--max NxM— fit within NxM box (preserves aspect).--exact NxM— force exact dimensions (may distort or crop).
- Output mode —
in-place(overwrite) or--output-dir <path>(default:<input>/resized/). - Filter — interpolation kernel:
lanczos3(default — best quality),cubic,linear,nearest. - Recursive —
--recursiveto descend into subdirectories. Default: top-level only. - Format preserve — by default keeps source format.
--to <ext>to change format on the way out.
Procedure
-
Verify
vipsis on PATH. If missing, fall back to ImageMagickconvertwith the same parameters and warn that this will be slower (point atinstall-deps). -
Enumerate input files (filter to image extensions: jpg, jpeg, png, webp, tiff, gif, heic, avif, jxl).
-
For each file, build the vips command. Two main forms:
Fit within box (preserves aspect):
vipsthumbnail "<input>" --size "<W>x<H>" --output "<output>[Q=85]"vipsthumbnailis the right tool for "resize down" — it's optimised for thumbnail-style ops and handles JPEG shrink-on-load (free 8× speedup for 1/8-size targets).Exact resize via
vips:vips resize "<input>" "<output>" <scale-factor> --kernel <kernel>
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.
- 2mo ago First seen · 72 lines · 74 tokens per session scan A dbc79d2618c1
fast-resize is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 991 once invoked, about $0.0003 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 2026-08-30.
fast-resize compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fast-resizedanielrosehill/Claude-Image-Production-Plugin | Skill | 21 | yesterday | MIT | A | 74 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |