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.
npx skills add CharlesWiltgen/Axiom --skill axiom-aigit 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/skills/charleswiltgen/axiom/axiom-ai)<a href="https://agentmods.dev/skills/charleswiltgen/axiom/axiom-ai"><img src="https://agentmods.dev/badge/skills/charleswiltgen/axiom/axiom-ai/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/skills/charleswiltgen/axiom/axiom-ai"><img src="https://agentmods.dev/badge/skills/charleswiltgen/axiom/axiom-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00057 | $0.06036 |
| Opus 5.5 | $0.00023 | $0.02414 |
| Sonnet 5.5 | $0.00011 | $0.01207 |
| Haiku 4.5 | $0.00006 | $0.00604 |
Grade A, and why
axiom-ai 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 12d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Intelligence & AI
You MUST use this skill for ANY Apple Intelligence or Foundation Models work.
Can't launch Axiom agents? Where this router sends you to an agent, follow its procedure inline. Over MCP,
axiom_get_agentreturns it; elsewhere, read its file below, which needs only file search and read.Available here:
skills/foundation-models-auditor.md.For any other agent, over MCP
axiom_get_agentreturns it too; run its xclog, xcsym and xcprof steps with theaxiom_xclog_*,axiom_xcsym_*andaxiom_xcprof_*tools. Elsewhere, search Axiom's skills forskills/<agent>.md; if there is none, do that work yourself with this suite's skills, using any Axiom tool on yourPATH.
When to Use
Use this router when:
- Implementing Apple Intelligence features
- Using Foundation Models
- Working with LanguageModelSession
- Generating structured output with @Generable
- Debugging AI generation issues
- iOS 26 on-device AI
AI Approach Triage
First, determine which kind of AI the developer needs:
| Developer Intent | Route To |
|---|---|
| On-device text generation (Apple Intelligence) | Stay here → Foundation Models skills |
| Custom ML model deployment (PyTorch, TensorFlow) — classic Core ML | See skills/ios-ml.md (hub) → conversion / compression / training / deployment / ref / diag files |
| Core ML model fails to load, is slow, grows memory, or loses accuracy after compression | See skills/coreml-diag.md |
| Custom LLM-scale / transformer model on-device (27-cycle) | See skills/core-ai.md → Core AI conversion, runtime, specialization |
| Computer vision (image analysis, OCR, segmentation) | /skill axiom-vision → Vision framework |
| Cloud API integration (OpenAI, generic HTTP) | /skill axiom-networking → URLSession patterns |
| Cloud Claude integration (Anthropic SDK, Messages API, Claude Agent SDK) | See claude-api skill (external) → includes automated Opus 4.6 → 4.7 migration |
| Speech-to-text / transcription (SpeechAnalyzer, SpeechTranscriber, DictationTranscriber, mic → transcript) | See skills/speech.md (OS27 input providers, Swift 6 mic-tap isolation, the ~2-analyzer cap on iOS/visionOS; none on macOS) |
Turnkey Apple Intelligence UI — suggested actions for a messaging conversation (OS27) |
See skills/suggested-actions.md → drop-in SuggestedActionsView, entitlement-gated |
| System AI features (Writing Tools, Genmoji) | No custom code needed — these are system-provided |
What ships with it
22 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.
- skills/core-ai.md 19 KB
- skills/coreml-compression.md 6.3 KB
- skills/coreml-conversion.md 7.7 KB
- skills/coreml-deployment.md 18 KB
- skills/coreml-diag.md 17 KB
- skills/coreml-ref.md 21 KB
- skills/coreml-training.md 7.9 KB
- skills/foundation-models-adapters-diag.md 23 KB
- skills/foundation-models-adapters-ref.md 32 KB
- skills/foundation-models-adapters.md 25 KB
- skills/foundation-models-auditor.md 33 KB
- skills/foundation-models-diag.md 40 KB
- skills/foundation-models-evaluations-diag.md 23 KB
- skills/foundation-models-evaluations-ref.md 37 KB
- skills/foundation-models-evaluations.md 50 KB
- skills/foundation-models-guardrails.md 10 KB
- skills/foundation-models-ref.md 63 KB
- skills/foundation-models.md 50 KB
- skills/ios-ml.md 5.3 KB
- skills/speech.md 35 KB
- skills/suggested-actions.md 4.1 KB
- skills/training-paths.md 6.9 KB
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.
- 12d ago Changed b730bfbed87d
- 14d ago Changed · +11 lines 27ffe0e9f60e
- 15d ago Changed 391736516d22
- 1mo ago First seen · 296 lines · 57 tokens per session scan A e91823670a13
axiom-ai is a skill published in the GitHub repository CharlesWiltgen/Axiom (1,230 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 6,036 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-06.
Other skills, from other repositories
ml-kit-genai-prompt-api
Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use structured output with Prompt API, implement prefix caching, optimize the current prompt, or apply best practices.".
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
ml-kit-genai-prompt-api
Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use structured output with Prompt API, implement prefix caching, optimize the current prompt, or apply best practices.".
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
firebase-ai-logic
Use for Firebase AI Logic and Gemini integration in Android, safe prompts, privacy boundaries, model selection, fallback behavior and not exposing private keys.
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. Use when adding on-device LLM features with Apple FoundationModels on iOS 26+.