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 gaelic-ghost/socket --skill vision-image-analysis-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/vision-image-analysis-workflow)<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/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/gaelic-ghost/socket/vision-image-analysis-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/vision-image-analysis-workflow.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 | $0.00079 | $0.01198 |
| Opus 5.5 | $0.00032 | $0.00479 |
| Sonnet 5.5 | $0.00016 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
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 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 — 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-workflowwhen a custom Core ML model supplies classification, detection, or segmentation. - Recommend
core-image-processing-workflowwhen the primary job changes pixels rather than interpreting them.
Single-Path Workflow
- 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
- 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
- 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
- Execute and interpret:
- use
ImageRequestHandleror the documented current request execution surface for new code - use
VNImageRequestHandlerfor independent original-API images andVNSequenceRequestHandlerwhen 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
- use
- 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
- Return documented behavior, request family, input contract, coordinate transform, lifecycle plan, observations, diagnostics, validation, and handoffs.
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.
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 · 92 lines · 79 tokens per session scan A cf6f2319d1f3
vision-image-analysis-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,198 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
chief-data-officer
Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
data-engineering
Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone…
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.
flutter-screenshots
Automate App Store & Google Play screenshot generation for Flutter apps. Scans routing and screens, scores high-value marketing screens, generates self-contained mock harness, runs native simulator captures (iPhone 6.9", iPad 13", Android Phone/Tablet), strips alpha channels, and validates exact store resolutions.