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 to-jxlgit 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/to-jxl)<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/to-jxl"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/to-jxl/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/to-jxl"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/to-jxl.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 | $0.00061 | $0.00897 |
| Opus 5.5 | $0.00024 | $0.00359 |
| Sonnet 5.5 | $0.00012 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade B, and why
to-jxl scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
command -v cjxl || echo "cjxl not installed — install with: sudo apt install libjxl-tools" How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convert Images to JPEG XL
Encode images to JPEG XL (.jxl) format using cjxl. Supports lossless, visually lossless, and web quality presets, with optional effort (compression) tuning.
When to use
- Converting photos to JXL for archival, where file size matters and quality must be preserved.
- Lossless-transcoding existing JPEG files to save ~20% file size without re-compression artifacts.
- Creating web-optimized JXL variants with controlled visual loss.
Inputs to gather
- Input file or directory — single image, folder, or recursive tree. If omitted, ask for the path.
- Quality preset — ask which tier:
lossless(full fidelity,-d 0),visually-lossless(imperceptible loss,-d 1.0, default), orweb(visible compression acceptable,-d 3.0). Default: visually-lossless. - Effort level — optional, range 1–9 (1 = fastest, 9 = slowest/best compression). Default: 7. Only ask if the user is concerned about speed vs file size.
Procedure
1. Check tooling
command -v cjxl || echo "cjxl not installed — install with: sudo apt install libjxl-tools"
Abort if missing.
2. Map quality presets to distance
lossless→-d 0visually-lossless→-d 1.0web→-d 3.0
Set effort=7 unless the user overrides.
3. Determine scope
- Single file: run one conversion.
- Directory (non-recursive): ask before processing, then loop over image files in the folder.
- Recursive: use
findto locate all images in the tree.
Ask for confirmation before batch operations.
4. Convert
Single file:
cjxl -d <distance> -e <effort> input.jpg output.jxl
Batch (folder or recursive):
find <target> -maxdepth <1|999> -type f \
\( -iname '*.jpg' -o -iname '*.jpeg' -o -iname '*.png' \
-o -iname '*.gif' -o -iname '*.webp' -o -iname '*.tif' \) \
-exec cjxl -d <distance> -e <effort> {} {.}.jxl \;
Show progress (file count, time remaining estimate if batch is large).
5. Report
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 · 88 lines · 61 tokens per session scan B c5930d3c403e
to-jxl is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 897 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
to-jxl compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| to-jxldanielrosehill/Claude-Image-Production-Plugin | Skill | 21 | yesterday | MIT | B | 61 | 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 |