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-thumbnailgit 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-thumbnail)<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/fast-thumbnail"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/fast-thumbnail/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-thumbnail"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/fast-thumbnail.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 | $0.00056 | $0.00850 |
| Opus 5.5 | $0.00022 | $0.00340 |
| Sonnet 5.5 | $0.00011 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
fast-thumbnail 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast Thumbnail (vipsthumbnail)
Generate thumbnails at high throughput using vipsthumbnail. Distinct from fast-resize: this is purpose-built for "make small previews of every image in this folder" workflows where output is always a downscale and quality is "good enough for a thumbnail".
When to use
- Building a contact-sheet / web-gallery / index of an image library.
- Pre-rendering thumbnails for a UI / filesystem browser.
- Bulk-shrinking large originals to share / archive.
Do not use this skill when:
- The user wants the same size as the originals — that's a no-op.
- The user is upscaling — use
fast-resize(orupscale-imagefor AI upscale). - The user wants to keep original quality — this skill assumes lossy thumbnail-grade output.
Inputs
- Input directory — required.
- Size — pixel size. Single number is shorthand for
NxN(fit within square). Default:512. - Output dir — default:
<input>/thumbnails/. The skill never overwrites originals. - Format — output format. Default:
jpg(best size/quality balance for thumbs). Options:jpg,png,webp,avif. - Quality — JPEG/WebP/AVIF quality. Default:
80. - Recursive —
--recursiveto descend. Mirrors subdirectory structure under the output dir. - Naming — default: same base name.
--prefix <s>or--suffix <s>if collision is a risk.
Procedure
-
Verify
vipsthumbnailis on PATH. If missing, point atinstall-deps. No graceful fallback — if vips isn't installed, the skill's whole reason to exist is gone; tell the user to install or usebatch-resize. -
Enumerate input files (image extensions only).
-
For each file:
vipsthumbnail "<input>" \ --size "<size>" \ --output "<output-dir>/<basename>.<ext>[Q=<quality>]"For non-JPEG outputs, the
[Q=N]syntax still works for WebP/AVIF. -
For very large batches, parallelise with
find ... | xargs -P <ncpu> -I{} vipsthumbnail .... vips is internally threaded but per-image work is small enough that process-level parallelism wins on >5k batches.
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 · 63 lines · 56 tokens per session scan A 0184962918d0
fast-thumbnail is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 850 once invoked, about $0.0002 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-thumbnail compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fast-thumbnaildanielrosehill/Claude-Image-Production-Plugin | Skill | 21 | yesterday | MIT | A | 56 | 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 |