vision-framework

vision-framework is a skill for Claude Code, Codex from TalissonVitorino/kmp-ios-skills. It costs 237 tokens per session (4,530 once invoked), scanned A, original, MIT.

An iOS image-analysis guide for reading text, detecting faces and barcodes, scanning documents, tracking objects, and running Core ML models on a device. It explains Apple's Vision framework and VisionKit's scanning interface, including which APIs work on different iOS versions.

In plain words
What is it for?
Use it for OCR of cards, cheques, and IDs; barcode or QR scanning; document capture for customer identity checks; face detection; object tracking; and custom on-device machine-learning inference.
Why use it?
It helps developers add image processing without sending sensitive financial or identity data off the phone. It also avoids confusion between similar Apple APIs and supports both newer and older iOS versions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it for OCR of cards, cheques, and IDs; barcode or QR scanning; document capture for customer identity checks; face detection; object tracking; and custom on-device machine-learning inference.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/talissonvitorino/kmp-ios-skills/vision-framework
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 TalissonVitorino/kmp-ios-skills --skill vision-framework
Clone the repo
git clone --depth 1 https://github.com/TalissonVitorino/kmp-ios-skills

Made for: Claude Code, Codex.

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-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/vision-framework/github.svg)](https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/vision-framework)
Your own site
<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/vision-framework"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/vision-framework/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.

agentmods 80×15 button for vision-framework

Your own site · 80×15
<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/vision-framework"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/vision-framework.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 237 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,530 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 medium

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 →

  • medium Rogue Agent · line 201
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00237 $0.04530
Opus 5 $0.00118 $0.02265
Sonnet 5 $0.00047 $0.00906
Haiku 4.5 $0.00024 $0.00453

Measured 6d ago against content hash 3c83f671b272, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vision-framework 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 6d 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.

ios/vision-framework/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision & VisionKit (iOS)

On-device computer vision for a fintech app: OCR of cards/cheques/IDs, barcode/QR scanning, document capture for KYC, and custom Core ML inference. Everything here runs on device — no image ever leaves the phone, which is the right posture for KYC/PII. Grounded in Apple's Vision and VisionKit frameworks.

  • Two Vision APIs coexist. The modern Swift API (RecognizeTextRequest, struct/class requests with async .perform(on:)) needs iOS 18+. The legacy API (VNRecognizeTextRequest + VNImageRequestHandler) works back to iOS 13 and is still the path when you support iOS 17 or earlier. Same ML models underneath; different surface.
  • VisionKit is a separate framework for UI: full-screen live scanners and Live Text overlays. Reach for it before hand-rolling an AVCaptureSession + Vision loop.
  • Do NOT confuse with visionOS. This skill is Apple's image-analysis Vision, unrelated to the Apple Vision Pro platform.

Contents

Which API to use

You need… Use Min iOS
Still-image OCR / detection, new code, iOS 18+ only Modern Vision (RecognizeTextRequest, …) 18
Same, but supporting iOS 17 or earlier Legacy Vision (VNRecognizeTextRequest + VNImageRequestHandler) 13
Full-screen live camera scanner (text + codes), minimal code VisionKit DataScannerViewController 16
Guided multi-page document scan (edge detect, deskew, capture) VisionKit VNDocumentCameraViewController 13
Live Text selection/data-detectors over a static image VisionKit ImageAnalyzer + ImageAnalysisInteraction 16
Run your own trained classifier/detector CoreMLRequest (modern) / VNCoreMLRequest (legacy) 18 / 11

Read the full file on GitHub · 310 lines

Files

What ships with it

3 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. 6d ago First seen · 310 lines · 237 tokens per session scan A 3c83f671b272

Subscribe to this mod's changes

vision-framework is a skill published in the GitHub repository TalissonVitorino/kmp-ios-skills (12 stars, last pushed 15d ago), licensed MIT. It adds 237 tokens to every session and 4,530 once invoked, about $0.0012 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

compose-multiplatform

Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…

ericrisco/rsc-harness · 80 tokens

cmp-new

Scaffold a new MOBILE app — Android + iOS from one Kotlin/Compose Multiplatform codebase — from a bare "create a mobile app" to a green, verified build. Guardrails first: if the user already chose a different framework (React Native, Expo, Flutter, SwiftUI, native), do NOT redirect them here; if they only asked a…

kvdm-co-pilot/create-cmp · 478 tokens

cmp-firebase-connect

Wire a freshly scaffolded CMP/KMP app to its OWN real Firebase project — the #1 post-scaffold manual step. Use this when the user wants to connect their app to Firebase, or asks "connect my app to firebase", "set up google-services.json", "wire firebase", "create a firebase project for this app", "replace the…

kvdm-co-pilot/create-cmp · 170 tokens

cmp-audit

Adversarial audit of one subsystem of a Kotlin/Compose Multiplatform app against its spec AND against platform semantics — the class of defect desktop-tier tests cannot see (alarms, notifications, PendingIntents, reboot, process death, DST). Use this when the user says "audit the notifications", "double check X for…

kvdm-co-pilot/create-cmp · 157 tokens

add-feature

Add a new conforming vertical-slice feature (Screen + ViewModel + UseCase + Repository + spec + tests + golden tree + nav route + DI wiring) to this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature (qa/approvals.json's exemplarFeature — home by default). Use this when…

kvdm-co-pilot/create-cmp · 169 tokens

add-screen

Add a presentation-only slice — Screen + ViewModel + tests + golden tree + spec + nav route — for an EXISTING entity/repository in this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature's presentation layer (qa/approvals.json's exemplarFeature — home by default).…

kvdm-co-pilot/create-cmp · 202 tokens