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 from-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/from-jxl)<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/from-jxl"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/from-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/from-jxl"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/from-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 | $0.00039 | $0.00764 |
| Opus 5.5 | $0.00016 | $0.00306 |
| Sonnet 5.5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade B, and why
from-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 djxl || echo "djxl not installed — install with: sudo apt install libjxl-tools" How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decode JPEG XL Images
Extract images from JPEG XL (.jxl) files using djxl. Outputs PNG or JPEG, with optional recovery of original JPEG bitstream if the source JXL was a lossless JPEG transcode.
When to use
- Converting JXL files back to PNG for general use or compatibility.
- Recovering the original JPEG bitstream from a lossless-transcoded JXL file via
djxl --jpeg. - Batch-decoding a JXL archive to portable formats.
Inputs to gather
- Input .jxl file or directory — single file or folder.
- Output format —
png(default) orjpeg. If the user has a JXL that came from a lossless JPEG transcode and wants to recover the original JPEG byte-exact, offer thejpegformat and explain the--jpegflag. - Output directory — optional. Default: same directory as input.
Procedure
1. Check tooling
command -v djxl || echo "djxl not installed — install with: sudo apt install libjxl-tools"
Abort if missing.
2. Determine scope and format
- Single file: direct conversion.
- Directory (non-recursive): loop over all
.jxlfiles. - Recursive: use
findto locate.jxlfiles in the tree.
Confirm the output format with the user.
3. Decode
Single file to PNG (default):
djxl input.jxl output.png
Single file to JPEG (standard):
djxl input.jxl output.jpg
Single file to original JPEG (lossless transcode recovery):
If the JXL was created via cjxl in.jpg out.jxl, this recovers the original JPEG bitstream byte-exact:
djxl --jpeg input.jxl recovered.jpg
Batch (folder or recursive):
find <target> -maxdepth <1|999> -type f -iname '*.jxl' \
-exec djxl {} {.}.<format> \;
(Replace <format> with png or jpg, or —jpeg flag for JPEG recovery.)
4. Report
After decoding:
- Count of files decoded, skipped, failed.
- Output file sizes and locations.
- If batch, show a summary of converted files.
Output / side effects
- New PNG or JPEG files created in the output directory.
- Original
.jxlfiles remain unchanged.
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 · 92 lines · 39 tokens per session scan B f831f0236492
from-jxl is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (21 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 764 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.
from-jxl compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| from-jxldanielrosehill/Claude-Image-Production-Plugin | Skill | 21 | yesterday | MIT | B | 39 | 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 |