verification-loop

verification-loop is a skill for Claude Code, Codex from troyjthomas/ios-agent-skills. It costs 74 tokens per session (1,714 once invoked), scanned A, original, MIT.

A checklist for proving that a mobile app’s interface really changed as intended, using simulator checks, accessibility layout data, and repeatable tests. It covers the steps between making a UI fix and confirming it works.

In plain words
What is it for?
Verifying layout fixes, tap gestures, and visual bugs in an iOS simulator before declaring them finished.
Why use it?
Screenshots can look correct while spacing, alignment, button size, or gestures are still wrong. This replaces visual guesswork with measured checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/troyjthomas/ios-agent-skills/verification-loop
Any agent
npx skills add troyjthomas/ios-agent-skills --skill verification-loop
Clone the repo
git clone --depth 1 https://github.com/troyjthomas/ios-agent-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 verification-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/verification-loop.svg)](https://agentmods.dev/skills/troyjthomas/ios-agent-skills/verification-loop)
Your own site
<a href="https://agentmods.dev/skills/troyjthomas/ios-agent-skills/verification-loop"><img src="https://agentmods.dev/badge/skills/troyjthomas/ios-agent-skills/verification-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,714 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 5.1 $0.00074 $0.01714
Opus 5 $0.00037 $0.00857
Sonnet 5 $0.00015 $0.00343
Haiku 4.5 $0.00007 $0.00171

Measured 6d ago against content hash 7eb9d9076183, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verification-loop 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.

skills/verification-loop/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Loop

The testing-strategy skill covers automated build verification, unit tests, and manual testing — three layers that prove the code is correct, the logic is correct, and the user experience is correct on a real device.

This skill covers the layer in between: the visual verification loop you run on simulator while iterating. It's where most "I fixed it!" → "actually no you didn't" cycles happen, because eyeballing a screenshot is unreliable for layout bugs.

When to Use

  • Iterating on a layout, padding, alignment, or sizing fix
  • Hooking up a new gesture and need to confirm it fires
  • Diagnosing a visual bug from a user screenshot
  • Before claiming any UI fix is "done" — required reading

Why Screenshots Alone Aren't Enough

Humans cannot reliably eyeball:

  • 16pt vs 21pt padding
  • 2pt off-center drift
  • 40pt vs 44pt button heights
  • A view extending 4pt past where it should

Every one of those is a real bug that ships in apps that "looked fine on simulator." The verification loop replaces "looks fine" with "the AX frame says width 396.66pt, parent says width 402, so right margin is 5.34pt — symmetric with the left's 24pt? No, off by 19pt — fix it."

The Four-Step Loop

After every UI change, before claiming a fix is done:

1. Build clean

Build with XcodeBuildMCP. If status is SUCCEEDED with zero errors,
proceed. If SourceKit reports phantom diagnostics that don't show
up in the actual build log (e.g. "Cannot find type X" while the
build log shows zero errors), ignore them — see the
xcode-integration skill for the SourceKit-lag distinction.

2. Screenshot

Capture the screen state. Useful for "does it look right?" gut-check
but NEVER sufficient on its own for layout claims.

3. AX snapshot — the critical step

XcodeBuildMCP's snapshot_ui returns the accessibility tree with every visible element's AXFrame (x, y, width, height) in real screen coordinates. Use this to verify layout numerically:

Get the AX snapshot. For the view you changed, locate its frame
in the output. Compare against:
- The parent's frame (is the child centered? offset? overlapping?)
- Sibling frames (is spacing equal? is alignment matching?)
- Screen bounds (is anything off-screen?)
- The expected values from the design (does padding match the spec?)

Read the full file on GitHub · 172 lines

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 · 172 lines · 74 tokens per session scan A 7eb9d9076183

Subscribe to this mod's changes

verification-loop is a skill published in the GitHub repository troyjthomas/ios-agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,714 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 2026-08-31.

Related

Other skills, from other repositories

swift-testing

Write and migrate tests using the Swift Testing framework with @Test, @Suite, #expect, #require, confirmation, parameterized tests, test tags, traits, withKnownIssue, XCTest UI testing, XCUITest, test plan, mocking, test doubles, testable architecture, snapshot testing, async test patterns, test organization, and…

JordanCoin/ios-skills-collection · 113 tokens

ios-simulator-skill

21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.

JordanCoin/ios-skills-collection · 47 tokens

asc-shots-pipeline

Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (asc screenshots frame), and screenshot upload (asc screenshots upload). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition…

rorkai/app-store-connect-cli-skills · 79 tokens

t-flutter-demo-run-all

Run all Android Patrol user-story demo files with resumable checkpoints.

timzaak/web-dev-skills · 20 tokens

android-ui-verification-v2

Android UI Verification Skill workflow skill. Use this skill when the user needs Automated end-to-end UI testing and verification on an Android Emulator using ADB and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

diegosouzapw/awesome-omni-skills · 57 tokens

ui-crawler-max

Autonomous UI crawler for iOS simulator apps — rapid, element-precise data collection. Use whenever the user says "crawl my app", "auto-test the UI", "click/tap through every screen", "monkey test", "explore the app and find errors/crashes", "collect screenshots of all screens", "smoke test the whole app", or asks for…

Dev869/swift-tothemax · 179 tokens