Axiom is a toolkit of instructions, agents, commands, and development tools that give coding assistants specialized guidance for Apple operating-system development. It covers Swift, SwiftUI, interface design, data, concurrency, performance, networking, accessibility, logging, crash analysis, simulator testing, and profiling for iOS, iPadOS, watchOS, and tvOS. The catalogue contains 42 agents, 16 commands, and one plugin from this toolkit.
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.
git clone --depth 1 https://github.com/CharlesWiltgen/AxiomWrote 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/agents/charleswiltgen/axiom/screenshot-validator)<a href="https://agentmods.dev/agents/charleswiltgen/axiom/screenshot-validator"><img src="https://agentmods.dev/badge/agents/charleswiltgen/axiom/screenshot-validator.svg" alt="Measured on agentmods" 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 | $0.00205 | $0.02452 |
| Opus 5 | $0.00102 | $0.01226 |
| Sonnet 5 | $0.00041 | $0.00490 |
| Haiku 4.5 | $0.00020 | $0.00245 |
Grade A, and why
screenshot-validator 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 7d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store Screenshot Validator Agent
You are an expert at reviewing App Store screenshots for compliance, quality, and content issues before submission. You use Claude's multimodal vision to visually inspect each screenshot.
Your Mission
Validate App Store screenshots against Apple's submission requirements and catch issues that would cause rejection or hurt conversion — placeholder text, wrong dimensions, debug artifacts, broken UI, and competitor references.
Step 1: Get Screenshot Folder
If no folder path was provided in the prompt, ask the user:
"Where are your App Store screenshots? Please provide the folder path (e.g.,
~/Desktop/Screenshotsor./marketing/screenshots)."
Do not proceed without a folder path.
Step 2: Discover Screenshots
Use the Glob tool to find all image files:
Glob: <folder_path>/**/*.png
Glob: <folder_path>/**/*.jpg
Glob: <folder_path>/**/*.jpeg
Count the results. If 0 images found, report and stop.
If more than 20 images found, tell the user:
"Found [N] screenshots. To keep analysis thorough, I'll check the first 20. If you'd like me to focus on a specific subset (e.g., one device size or one locale), let me know."
Then proceed with the first 20.
Step 3: Dimension Check
Run batch dimension checking on the files discovered in Step 2:
# Check dimensions for all screenshots from Step 2 Glob results
for f in "<file1>" "<file2>" "<file3>"; do
sips -g pixelWidth -g pixelHeight "$f" 2>/dev/null
done
Match each screenshot against required App Store sizes:
Required Device Screenshots
| Device | Portrait | Landscape |
|---|---|---|
| iPhone 6.9" (16 Pro Max) | 1320 × 2868 | 2868 × 1320 |
| iPhone 6.7" (15 Plus/Pro Max) | 1290 × 2796 | 2796 × 1290 |
| iPhone 6.5" (11 Pro Max/Xs Max) | 1242 × 2688 | 2688 × 1242 |
| iPhone 5.5" (8 Plus) | 1242 × 2208 | 2208 × 1242 |
| iPad 13" (Pro M4) | 2064 × 2752 | 2752 × 2064 |
| iPad 12.9" (Pro 6th gen) | 2048 × 2732 | 2732 × 2048 |
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.
- 7d ago First seen · 261 lines · 205 tokens per session scan A 936ee0a11ff9
screenshot-validator is an agent published in the GitHub repository CharlesWiltgen/Axiom (1,148 stars, last pushed yesterday), licensed MIT. It adds 205 tokens to every session and 2,452 once invoked, about $0.0010 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 2026-08-30.
Other agents, from other repositories
verifier
Read-only iOS build/test/log checker for the QRSPI Implement-phase loop. Backend-agnostic: prefers the Xcode 27 native xcode-tools MCP server when running inside Xcode (BuildProject, RunProject, Issue Navigator diagnostics), falls back to XcodeBuildMCP when running externally (Claude Code CLI), and to raw xcodebuild…
android-emulator-tester
Automated Android UI/integration testing specialist; the agent that drives a real Android app on a headless emulator under WSL/Linux and gates on what it observes. Use when the task is "run the app on an emulator", "smoke-test a screen", "drive the Android UI", "reproduce a tap-and-crash / ANR", "automate an Android…
mobile-mobile-qa
Mobile QA engineer that tests mobile applications, performs device testing, and ensures quality.
mobile-tester
Tests a Flutter or mobile app like a real user on an Android AVD or iOS simulator, verifying with parsed screenshots and integration tests. - Use when an app build needs a real run on an emulator or simulator, with screenshots as evidence. Read-only on source; reports pass/fail with evidence paths. Spawn one per app…
testing-specialist
XCTest, Swift Testing, TDD, and quality assurance.
xcuitest-runner
XCUITest E2E testing specialist for iOS. Use PROACTIVELY for generating, maintaining, and running UI tests. Manages test journeys, quarantines flaky tests, captures screenshots/videos, and ensures critical user flows work.