transcode-jpeg-to-jxl-lossless

transcode-jpeg-to-jxl-lossless is a skill for Claude Code from danielrosehill/Claude-Image-Production-Plugin. It costs 54 tokens per session (1,212 once invoked), scanned B, original, MIT.

A skill that converts JPEG images to JPEG XL files using lossless encoding, preserving the original JPEG data rather than recompressing the image. It can process directories and report the resulting byte savings.

In plain words
What is it for?
Use it to archive JPEG photo collections, optionally process subfolders, preview savings, and create JPEG XL files for long-term storage.
Why use it?
It can reduce archive size without degrading image quality, while retaining a way to recover the original JPEG bitstream.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the image-production plugin — 29 skills, 19 commands shipped together

Good fit Use it to archive JPEG photo collections, optionally process subfolders, preview savings, and create JPEG XL files for long-term storage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless
Install

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.

Any agent
npx skills add danielrosehill/Claude-Image-Production-Plugin --skill transcode-jpeg-to-jxl-lossless
Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-Image-Production-Plugin

Made for: Claude Code.

Or install image-production, the plugin that ships this one along with the rest of its 29 skills, 19 commands.

Wrote 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.

agentmods badge for transcode-jpeg-to-jxl-lossless

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless)
Your own site
<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless/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.

agentmods 80×15 button for transcode-jpeg-to-jxl-lossless

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/transcode-jpeg-to-jxl-lossless.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,212 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.01212
Opus 5 $0.00027 $0.00606
Sonnet 5 $0.00011 $0.00242
Haiku 4.5 $0.00005 $0.00121

Measured 12d ago against content hash 0007d65f1fba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

transcode-jpeg-to-jxl-lossless 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 12d 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"
skills/transcode-jpeg-to-jxl-lossless/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Losslessly Transcode JPEG to JPEG XL

Walk a directory of JPEG files and convert them to JPEG XL (.jxl) format using lossless encoding. cjxl automatically detects JPEG bitstream and preserves it without re-compression. Reports byte savings; explains how to recover the original JPEG if needed.

When to use

  • Archiving JPEG photo libraries to save space (typically 15–25% reduction) without image degradation.
  • Preparing a photo collection for long-term storage where compatibility with JPEG is not required.
  • Building a smaller-footprint JXL archive that can still yield the original JPEG via djxl --jpeg.

Inputs to gather

  • Source directory — folder containing JPEG files (.jpg or .jpeg). Default: current directory.
  • Recursive? Ask whether to process subdirectories. Default: no (flat, current folder only).
  • Output location — optional. Default: same directory as originals (.jxl files sit alongside .jpg).
  • Dry run first? Recommend a preview pass showing the count and byte savings estimate, before committing to the conversion.

Procedure

1. Check tooling

command -v cjxl || echo "cjxl not installed — install with: sudo apt install libjxl-tools"

Abort if missing.

2. Preview

Show the user what will happen:

# Count JPEGs in scope
find <target> -maxdepth <1|999> -type f \
  \( -iname '*.jpg' -o -iname '*.jpeg' \) | tee /tmp/jpegs.txt | wc -l

# Estimate original size
find <target> -maxdepth <1|999> -type f \
  \( -iname '*.jpg' -o -iname '*.jpeg' \) -exec du -ch {} + | tail -1

Print:

  • Number of JPEG files found.
  • Total original size.
  • Estimated output size (advise 20% reduction as a rough baseline).
  • Confirm before proceeding.

3. Transcode

Use -d 0 (lossless) and a reasonable effort (suggest 6–7 for balance):

Folder (non-recursive):

find <target> -maxdepth 1 -type f \
  \( -iname '*.jpg' -o -iname '*.jpeg' \) \
  -exec cjxl -d 0 -e 7 {} {.}.jxl \;

Recursive:

Read the full file on GitHub · 122 lines

Changes

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.

  1. 12d ago First seen · 122 lines · 54 tokens per session scan B 0007d65f1fba

Subscribe to this mod's changes

transcode-jpeg-to-jxl-lossless is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (17 stars, last pushed 25d ago), licensed MIT. It adds 54 tokens to every session and 1,212 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens