Agent Vision Toolkit gives text-only coding agents tools for understanding images, including image questions, OCR for long screenshots, frontend reconstruction, and GUI automation. Developers use it to add visual capabilities to agents that cannot process images natively, with optional integrations for several coding-agent systems. The catalogue skill teaches agents how to use these vision tools.
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 Anionex/agent-vision-toolkit --skill vision-skillsgit clone --depth 1 https://github.com/Anionex/agent-vision-toolkitWrote 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/anionex/agent-vision-toolkit/vision-skills)<a href="https://agentmods.dev/skills/anionex/agent-vision-toolkit/vision-skills"><img src="https://agentmods.dev/badge/skills/anionex/agent-vision-toolkit/vision-skills/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/anionex/agent-vision-toolkit/vision-skills"><img src="https://agentmods.dev/badge/skills/anionex/agent-vision-toolkit/vision-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00132 | $0.04116 |
| Opus 5.5 | $0.00053 | $0.01646 |
| Sonnet 5.5 | $0.00026 | $0.00823 |
| Haiku 4.5 | $0.00013 | $0.00412 |
Grade A, and why
vision-skills 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 16d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vision-skills
Five local CLIs that give a text-only agent eyes. They read one shared
vision config (VISION_API_KEY / VISION_BASE_URL / VISION_MODEL /
LANG), plus the optional Python-client settings VISION_API_PROTOCOL,
VISION_REASONING_EFFORT, and VISION_USER_AGENT — no extra credentials.
Pick the tool by the question you are answering:
| Question | Tool |
|---|---|
| "What does this image show / say?" | glance |
| "Where is X?" — a thing you can name | ground |
| "Where are all the Xs?" — every instance of a kind | detect |
| "What is its exact shape, size, offset?" | trace |
| "Cut this box out as its own image file" | crop |
| "OCR this long screenshot / scrolling page / chat history" | scripts/long_screenshot_ocr.py |
| "Extract the icon/logo foreground as transparent PNG — manual region or auto (cropped+scaled screenshots)" | scripts/extract_fg.py |
| "Turn this HTML file into a viewport or full-page screenshot" | scripts/html_shot.py |
| "Which colours dominate a region, and which palette value fits it?" | scripts/dominant_colors.py |
| A relation none of them return — a gap, a distance between two located things | code over the pixels (Pillow) |
glance answers what something is; ground and detect answer where.
You give ground a description of a particular thing; you give detect a
kind and it enumerates the instances.
Both give real coordinates, but they are not pixel-exact: the box arrives
on a 0-1000 grid and is scaled to your image, so the last pixel or few are
not reliable. That is accurate enough to crop with, to click, to compare
positions against. When a number has to be exact, trace derives it from
the actual pixels — offsets, sizes, shapes.
Use the provided tools before hand-rolled pixels
Everything this toolkit ships a tool for, call the tool — do not rewrite it with Pillow in the middle of a task. The CLIs exist so the same pixel work is not hand-coded differently every time:
- cut a box out of an image →
crop, notImage.open(...).crop(...) - sample a region's palette →
scripts/dominant_colors.py - compare two images →
scripts/pixel_diff.py - vectorize to SVG →
trace - locate / inventory elements →
ground/detect - describe / OCR an image →
glance - safely split, OCR, and merge a long screenshot →
scripts/long_screenshot_ocr.py - HTML file to a viewport or full-page screenshot →
scripts/html_shot.py
What ships with it
12 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.
- agents/openai.yaml 242 B
- references/gui.md 3.9 KB
- references/long-screenshot-ocr.md 3.3 KB
- references/restore-graphic.md 3.7 KB
- references/restore-structure.md 1.9 KB
- references/restore-ui.md 10.0 KB
- scripts/dominant_colors.py 10.0 KB runs code
- scripts/extract_fg.py 12 KB runs code
- scripts/html_shot.py 23 KB runs code
- scripts/long_screenshot_ocr.py 44 KB runs code
- scripts/pixel_diff.py 3.9 KB runs code
- work/shot.png 694 KB
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.
- 16d ago Changed · +7 lines e8e1ebba1d4f
- 1mo ago First seen · 323 lines · 132 tokens per session scan A d902eab31823
vision-skills is a skill published in the GitHub repository Anionex/agent-vision-toolkit (1,249 stars, last pushed 11d ago), licensed MIT. It adds 132 tokens to every session and 4,116 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
figma-use
MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…
figma
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
frontend-design
A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.
prototype-workflow
Generate and lifecycle-manage HTML prototypes for UI exploration and OpenSpec changes. Use when creating, validating, completing, or archiving a UI prototype.
glmv-web-replication
Frontend visual replication skill. Explores a target website’s publicly visible pages via Playwright MCP or agent-browser, captures screenshots and layout information, then generates a static or client-side frontend replica that approximates the original’s visual appearance and page structure. This skill replicates…
Image Generation
Generate images from a text prompt. Uses Black Forest Labs Flux by default, with OpenAI DALL-E as an alternate.