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 easyzoom/aix-skills --skill tjpgd-integrationgit clone --depth 1 https://github.com/easyzoom/aix-skillsWrote 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/easyzoom/aix-skills/tjpgd-integration)<a href="https://agentmods.dev/skills/easyzoom/aix-skills/tjpgd-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/tjpgd-integration/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/easyzoom/aix-skills/tjpgd-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/tjpgd-integration.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 | $0.00041 | $0.00653 |
| Opus 5 | $0.00020 | $0.00327 |
| Sonnet 5 | $0.00008 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
tjpgd-integration 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 8d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TJpgDec Integration
Overview
Use this skill to integrate TJpgDec by proving the input callback, output callback, work buffer, color format, scaling, and display path. TJpgDec is small, but it still needs careful ownership of input streams and pixel blocks.
When To Use
Use this skill when:
- The user wants JPEG decoding on MCUs, small displays, LVGL image pipelines, or resource-constrained embedded systems.
- The issue involves decode errors, wrong colors, cropped images, slow rendering, memory faults, or display block callbacks.
- The project stores JPEGs in flash, filesystem, SD card, OTA resources, or network streams.
Do not use this skill when the display driver itself is not proven. Use lvgl-integration, u8g2-integration, or epd-integration as appropriate.
First Questions
Ask for:
- TJpgDec version or wrapper library, target MCU, RAM budget, and compiler.
- JPEG dimensions, subsampling, color format, progressive/baseline status, and asset source.
- Input storage path, read callback, seek/skip support, and chunk size.
- Output target: framebuffer, display flush, LVGL canvas, EPD buffer, or file.
- Current error code, work buffer size, and failing image sample.
Integration Checklist
-
Validate the JPEG format. Confirm baseline JPEG support and reject unsupported progressive or oversized images.
-
Prove input callback semantics. Reads, skips, short reads, and EOF must match TJpgDec expectations.
-
Allocate the work buffer deliberately. Keep the buffer aligned and sized for the selected build and platform.
-
Match output color. Convert RGB/BGR, RGB565 endian, grayscale, and alpha assumptions at the output boundary.
-
Clip and scale safely. Handle destination rectangles, scaling factors, and display bounds before pushing pixels.
-
Test multiple asset shapes. Include tiny, wide, tall, odd-sized, and maximum-resolution images.
Common Failures
- Using progressive JPEGs that the decoder does not support.
- Output callback writes past display or framebuffer bounds.
- RGB565 byte order is swapped.
- Input callback cannot skip bytes correctly for filesystem streams.
- Work buffer lives on a small task stack.
- Decoding blocks the UI or watchdog for too long.
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.
- 8d ago First seen · 83 lines · 41 tokens per session scan A fcd1d9953498
tjpgd-integration is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 653 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
github-social-preview
Generates a professional GitHub repository social preview image sized 1280x640 pixels as a JPG under 1 MB. Always trigger immediately when the user's message starts with "gsp". Also trigger on "generate github social preview", "create repo preview image", or any request to generate a social preview or OG image for a…
photo-rename
Rename photos using image analysis, GPS metadata, and web research to generate descriptive real-world filenames such as "grandcanyonphantomranch.jpg" or "eiffeltowerparis.jpg". Trigger immediately when the user's message starts with "rp", or when they upload photos and ask to rename, identify, or label them by…
container-home
Answer questions, assist with planning, and help with design decisions for Mick's off-grid shipping container lake home project. Trigger when the user mentions the container home, lake home, Stewart County, LBL, the expansion, solar system, septic permitting, or retirement property.
astrophotography-processing
Router for astrophotography processing, troubleshooting, and safe workflow guidance across deep-sky, narrowband, planetary/lunar/solar, Milky Way landscape, comet, and mosaic data.
digital-twin-sync
Synchronize construction digital twins with real-time data. Connect BIM models with IoT sensors, progress updates, and field data for live project visualization and monitoring.
drone-site-survey
Process drone survey data for construction sites. Generate orthomosaics, DEMs, point clouds, calculate volumes, track progress, and integrate with BIM models for comparison.