A local image-inspection workflow for text-only coding models, using OCR to read screenshots and tools to examine layouts, regions, pixels, and visual differences.

Use it to read screenshot text, inspect mockups, investigate image-based errors, compare pixels, identify regions, and analyze local visual layouts.

It provides evidence from local images when the coding model cannot directly understand what an image contains, without uploading images to the cloud.

sk-vision — Skill for Claude Code and OpenCode by MichelKerkmeester

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 MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-vision

Clone the repo

git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

Made for: Claude Code, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-vision/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-vision)

Your own site

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-vision"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-vision/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-vision"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,703 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Prompt Injection · line 8
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.04703
Opus 5	$0.00015	$0.02351
Sonnet 5	$0.00006	$0.00941
Haiku 4.5	$0.00003	$0.00470

Measured 8d ago against content hash 4c9fa2daa6e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sk-vision 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.

.opencode/skills/sk-vision/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sk-vision

Local vision skill. Text-only coding models get grounded OCR, layout, detect, and inspect evidence from a private Moondream runtime. The default posture is opt-in and idle. OpenCode does not register the tools by default. Pi registers them hidden. Cursor and Devin keep their MCP tools available. No API keys, no cloud upload, no per-image cost.

1. WHEN TO USE

Activation Triggers

Use this skill when the user invokes /vision or explicitly requests vision evidence for a local image. Route on any of:

screenshot OCR
attached image
mockup
error.png
local vision
moondream
grounded evidence
/vision
any request for the 13 sk_vision_* tools (inspect, detect, point, ocr, status, segment, metadata, crop, zoom, colors, diff, annotate, reverse)

The default posture is idle. The skill does not inspect attached images or advertise its tools unless the user invokes /vision, calls a tool on a host that exposes it, or sets SK_VISION_AUTOINSPECT=1 to restore the legacy OpenCode and Pi behavior.

Use Cases

Reading a screen the model cannot see

Extract exact text from a screenshot or error dialog (sk_vision_ocr).
Read a UI's structure: layout, elements and state (sk_vision_inspect).
Answer a specific question about an image (sk_vision_inspect with question).

Locating and measuring

Get labeled bounding boxes for objects or UI elements (sk_vision_detect).
Get normalized center coordinates for a target (sk_vision_point).
Cut out, upscale or mask a region (sk_vision_crop, sk_vision_zoom, sk_vision_segment).

Pixel analysis (no model required)

Read image dimensions, format and EXIF (sk_vision_metadata).
Read the dominant palette and luminance (sk_vision_colors).
Compare two images pixel-by-pixel (sk_vision_diff).
Annotate a copy for visual validation (sk_vision_annotate).
Reverse-search an image locally and on Yandex (sk_vision_reverse).

Read the full file on GitHub · 316 lines

Files

What ships with it

60 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.

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.

8d ago First seen · 316 lines · 29 tokens per session scan A 4c9fa2daa6e2

Subscribe to this mod's changes

sk-vision is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 4,703 once invoked, about $0.0001 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.

Debugging Design and UX

html-ppt-zhangzara-block-frame

Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.

nexu-io/open-design · 51 tokens

accesslint-scan

Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.

sickn33/agentic-awesome-skills · 32 tokens

check

Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.

tw93/Waza · 63 tokens

health

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…

tw93/Waza · 71 tokens

hunt

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code…

tw93/Waza · 70 tokens

think

Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask in any language for planning, architecture, design direction, feasibility, value judgment, or whether a feature is worth doing before implementation. Not for bug fixes or small edits.

tw93/Waza · 56 tokens

sk-vision

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

sk-vision

1. WHEN TO USE

Activation Triggers

Use Cases

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

html-ppt-zhangzara-block-frame

accesslint-scan

check

health

hunt

think