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/commands/charleswiltgen/axiom/screenshot)<a href="https://agentmods.dev/commands/charleswiltgen/axiom/screenshot"><img src="https://agentmods.dev/badge/commands/charleswiltgen/axiom/screenshot/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/commands/charleswiltgen/axiom/screenshot"><img src="https://agentmods.dev/badge/commands/charleswiltgen/axiom/screenshot.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 | $0.00011 | $0.00498 |
| Opus 5 | $0.00005 | $0.00249 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
screenshot 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- axiom-screenshot — 94% identical, 14 lines differ
What it actually says
Capture Simulator Screenshot
Take a screenshot of the currently booted iOS Simulator and display it for analysis.
What This Does
- Checks if a simulator is booted
- Captures screenshot to timestamped file
- Displays the screenshot (Claude is multimodal!)
- Returns the file path for reference
Usage
Simply run this command and Claude will:
- Execute:
xcrun simctl io booted screenshot /tmp/axiom-screenshot-<timestamp>.png - Read and display the screenshot
- Analyze what's visible in the screenshot
Prerequisites
- An iOS Simulator must be booted
- If no simulator is running, Claude will boot one first
Common Use Cases
Debug Visual Issues:
/axiom:screenshot
Then ask: "Does the login button look centered?"
Verify Fixes:
/axiom:screenshot
Then ask: "Is the text still clipped?"
Document Current State:
/axiom:screenshot
Claude will capture and describe the current UI state.
Physical devices & scriptable recording
This command shoots a simulator screenshot via simctl. To capture a physical
device, or to record video with a clean auto-stop (no Ctrl+C), use the unified
devicectl device capture path — one -d <udid> selector works for both sim and device
(Xcode 26.6+):
xcrun devicectl device capture screenshot -d <udid> --destination shot.png # .png required
xcrun devicectl device capture screen-record -d <udid> --destination clip.mp4 --duration 5
See the axiom-tools device-control reference (Screen capture) for codecs, mask policy,
and the simctl/axe fallbacks.
For More Control
For advanced simulator testing (location, push notifications, video recording, etc.), use:
/axiom:test-simulator
Or invoke the full simulator-tester agent with natural language:
- "Test my app with location simulation"
- "Send a test push notification"
- "Record a video of the app"
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.
- 9d ago First seen · 76 lines · 11 tokens per session scan A 6b072e75eb69
screenshot is a command published in the GitHub repository CharlesWiltgen/Axiom (1,151 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 498 once invoked, about $0.0001 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 commands, from other repositories
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
initialize-ios
Manual override: initialize ast-index for iOS/Swift/ObjC project.
maestro-selectors-instructions
Guide to using Maestro selectors for targeting UI elements in tests.
mobile-performance-check
Analyze mobile app for performance issues using the mobile-best-practices database.
flutter-review
Review Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.
flutter-test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.