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/plugins/charleswiltgen/axiom/axiom-cursor)<a href="https://agentmods.dev/plugins/charleswiltgen/axiom/axiom-cursor"><img src="https://agentmods.dev/badge/plugins/charleswiltgen/axiom/axiom-cursor.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
axiom 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 yesterday.
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.
What it actually says
{
"name": "axiom",
"version": "27.0.0-beta.53",
"description": "Battle-tested Cursor skills, agents, commands, hooks, and MCP for modern Apple platform development.",
"author": {
"name": "Charles Wiltgen",
"url": "https://charleswiltgen.github.io/Axiom/"
},
"homepage": "https://charleswiltgen.github.io/Axiom/",
"repository": "https://github.com/CharlesWiltgen/Axiom",
"license": "MIT",
"displayName": "Axiom",
"keywords": [
"ios",
"swift",
"swiftui",
"xcode",
"apple",
"mobile",
"development"
],
"logo": "assets/logo.svg"
}
What it installs
The manifest is a name and a version. 17 commands travel with it, and installing the plugin installs all of them — 374 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command axiom-health-check A 27 tokens
- Command axiom-status A 14 tokens
- Command axiom-optimize-build A 27 tokens
- Command axiom-run-tests A 19 tokens
- Command axiom-analyze-crash A 22 tokens
- Command axiom-triage A 40 tokens
- Command axiom-ui A 18 tokens
- Command axiom-compare-traces A 20 tokens
- Command axiom-console A 16 tokens
- Command axiom-profile A 15 tokens
- Command axiom-fix-build A 26 tokens
- Command axiom-audit A 16 tokens
- Command axiom-screenshot A 13 tokens
- Command axiom-test-simulator A 20 tokens
- Command axiom-ask A 24 tokens
- Command axiom-resolve-deps A 31 tokens
- Command axiom-modernize A 26 tokens
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.
- yesterday First seen · 24 lines scan A 9d70d816199d
axiom is a plugin published in the GitHub repository CharlesWiltgen/Axiom (1,148 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-06.
Other plugins, from other repositories
android-skills
Android and KMP development skills for Claude Code — architecture, Compose, coroutines, flows, networking (Retrofit, Ktor), persistent storage (Room, DataStore), pagination, dependency injection (Hilt, Koin), testing, debugging, Gradle, and Material Design 3.
ios-developer
iOS and Swift development with SwiftUI views and models.
swift-engineer
Elite iOS and macOS development expertise with automatic skill activation for Swift, UIKit, AppKit, SwiftUI, Xcode, and Apple frameworks plus code formatting tools.
mwdat-ios
Git-native DAT SDK guidance for ios development, covering setup, camera streaming, display access, MockDeviceKit, session lifecycle, permissions, debugging, and sample app patterns.
android-dev-skills
Android, Kotlin, Java, Gradle, testing, and release workflows.
compose-expert
Compose and Compose Multiplatform expert skill — state, animations, navigation, performance, design-to-code, PR review mode, M3 motion.