vision-image-analysis-workflow

vision-image-analysis-workflow is a skill for Claude Code, Codex from gaelic-ghost/socket. It costs 79 tokens per session (1,198 once invoked), scanned A, original, Apache-2.0.

A guide for using Apple Vision to understand images and video, such as finding text, barcodes, faces, shapes, people, poses, or tracked objects.

In plain words
What is it for?
Use it to add or repair built-in image analysis, including text recognition, barcode scanning, document detection, object tracking, pose detection, and image segmentation.
Why use it?
It helps developers select the appropriate Vision request and handle observations, coordinates, revisions, and correctness issues across still images and live video.

Skill for Claude CodeCodex

Part of the apple-dev-skills plugin — 65 skills, 2 MCP servers shipped together

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.

agentmods
npx agentmods add skills/gaelic-ghost/socket/vision-image-analysis-workflow
Any agent
npx skills add gaelic-ghost/socket --skill vision-image-analysis-workflow
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Or install apple-dev-skills, the plugin that ships this one along with the rest of its 65 skills, 2 MCP servers.

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 vision-image-analysis-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/gaelic-ghost/socket/vision-image-analysis-workflow.svg)](https://agentmods.dev/skills/gaelic-ghost/socket/vision-image-analysis-workflow)
Your own site
<a href="https://agentmods.dev/skills/gaelic-ghost/socket/vision-image-analysis-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/vision-image-analysis-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00079 $0.01198
Opus 5 $0.00039 $0.00599
Sonnet 5 $0.00016 $0.00240
Haiku 4.5 $0.00008 $0.00120

Measured yesterday against content hash cf6f2319d1f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vision-image-analysis-workflow 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 yesterday.

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.

plugins/apple-dev-skills/skills/vision-image-analysis-workflow/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision Image Analysis Workflow

Purpose

Guide Apple-provided image and video analysis while keeping Vision request ownership separate from image processing, custom Core ML model execution, capture, and biometric authentication.

When To Use

  • Use for built-in Vision detection, recognition, segmentation, tracking, pose, feature-print, request, observation, coordinate, and live-frame problems.
  • Recommend vision-coreml-recognition-workflow when a custom Core ML model supplies classification, detection, or segmentation.
  • Recommend core-image-processing-workflow when the primary job changes pixels rather than interpreting them.

Single-Path Workflow

  1. Classify the analysis:
    • text or document
    • barcode or machine-readable code
    • face rectangle or landmark
    • shape, contour, horizon, rectangle, saliency, or trajectory
    • human, hand, or animal pose
    • person, foreground, or instance segmentation
    • object tracking or sequence analysis
    • feature prints or similarity
    • coordinate, revision, performance, or correctness repair
  2. Apply the Apple docs gate:
    • read the current Vision documentation for the selected request and platform
    • choose the current Swift request API for new code when it supports the task
    • recognize the original VN* API explicitly when repairing existing code or when the current documented task requires it
    • state the documented behavior relied on
    • apply ../../shared/references/apple-vision-analysis-contract.md
  3. Define the input contract:
    • source type, dimensions, orientation, color/pixel format, region of interest, and frame identity
    • still-image versus sequence state
    • request revision or current Swift request availability
  4. Execute and interpret:
    • use ImageRequestHandler or the documented current request execution surface for new code
    • use VNImageRequestHandler for independent original-API images and VNSequenceRequestHandler when original-API requests need temporal state
    • keep observation types, normalized locations, confidence, labels, landmarks, and masks typed
    • convert coordinates through the full orientation, crop, region-of-interest, and display transform
  5. Control live work:
    • serialize stateful sequence requests
    • bound in-flight frames, cancel obsolete work where supported, and drop stale frames deliberately
    • publish results with the source frame identity so old observations cannot overwrite newer UI
  6. Return documented behavior, request family, input contract, coordinate transform, lifecycle plan, observations, diagnostics, validation, and handoffs.

Read the full file on GitHub · 92 lines

Files

What ships with it

4 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.

  1. yesterday First seen · 92 lines · 79 tokens per session scan A cf6f2319d1f3

Subscribe to this mod's changes

vision-image-analysis-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,198 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

app-store-optimization

Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.

cbrock84/headcount · 64 tokens

flutter-ui

Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.

datit309/supergraph · 48 tokens

flutter-dart-code-review

Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.

datit309/supergraph · 56 tokens

setup

Start DeployGate onboarding — set up app distribution from first upload to team-wide deployment.

DeployGate/deploygate-agent-plugin · 18 tokens

pipeline

Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…

kardebadas/claude-plugin · 80 tokens

sdk-setup

Add the DeployGate SDK to your Android app for crash reporting and screen capture.

DeployGate/deploygate-agent-plugin · 19 tokens