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 ssmurfgg04-gif/context-m --skill image-understandgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/image-understand)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/image-understand"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/image-understand/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/ssmurfgg04-gif/context-m/image-understand"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/image-understand.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 | $0.00063 | $0.05250 |
| Opus 5.5 | $0.00025 | $0.02100 |
| Sonnet 5.5 | $0.00013 | $0.01050 |
| Haiku 4.5 | $0.00006 | $0.00525 |
Grade A, and why
image-understand 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 1mo 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 — 856 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Understanding Skill
This skill provides specialized image understanding functionality using the z-ai-web-dev-sdk package, enabling AI models to analyze, describe, and extract information from static images.
Skills Path
Skill Location: {project_path}/skills/image-understand
this skill is located at above path in your project.
Reference Scripts: Example test scripts are available in the {Skill Location}/scripts/ directory for quick testing and reference. See {Skill Location}/scripts/image-understand.ts for a working example.
Overview
Image Understanding focuses specifically on static image analysis, providing capabilities for:
- Image description and scene understanding
- Object detection and recognition
- OCR (Optical Character Recognition) and text extraction
- Image classification and categorization
- Visual content analysis
- Quality assessment
- Accessibility (alt text generation)
IMPORTANT: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.
Prerequisites
The z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below.
CLI Usage (For Simple Tasks)
For quick image analysis tasks, you can use the z-ai CLI instead of writing code. This is ideal for simple image descriptions, testing, or automation.
Basic Image Analysis
# Describe an image from URL
z-ai vision --prompt "What's in this image?" --image "https://example.com/photo.jpg"
# Using short options
z-ai vision -p "Describe this image" -i "https://example.com/image.png"
Analyze Local Images
# Analyze a local image file
z-ai vision -p "What objects are in this photo?" -i "./photo.jpg"
# Save response to file
z-ai vision -p "Describe the scene" -i "./landscape.png" -o description.json
Multiple Images Comparison
# Compare multiple images
z-ai vision \
-p "Compare these two images and highlight the differences" \
-i "./photo1.jpg" \
-i "./photo2.jpg" \
-o comparison.json
# Analyze a series of images
z-ai vision \
--prompt "What patterns do you see across these images?" \
--image "https://example.com/img1.jpg" \
--image "https://example.com/img2.jpg" \
--image "https://example.com/img3.jpg"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 856 lines · 63 tokens per session scan A e8fc7d756a26
image-understand is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 63 tokens to every session and 5,250 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
prospect
Run a structured pre-mortem on a plan or approach BEFORE execution. Per-step risk enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, plan-formation diagnosis, action verdicts (PROCEED/SHRINK/SPLIT/DEFER/KILL)…
pptx
A guide for turning a paper, outline, or structured text into a PowerPoint presentation. It covers an 8–12-slide structure, concise slide points, and generation of a .pptx file.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
liteparse
Parse local document files into LLM-ready content on the daemon itself — PDFs → Markdown / structured JSON (with bounding boxes) / page screenshots via the bundled lit CLI. PDF works out of the box, offline, zero external deps (Tesseract + PDFium are bundled): digital PDFs use a near-instant native text path…
ingest
Read web pages and search the web through the workspace Load lane. A query or URL returns document outlines with refs; pass refs back to read the original text of the sections you need, batch several refs in one call, and follow nextRef only while more evidence is needed. Use whenever the user gives a URL, asks you to…
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.