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/The-Artificer-of-Ciphers-LLC/skills-from-the-artificerWrote 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/the-artificer-of-ciphers-llc/skills-from-the-artificer/on-device-ai-architect)<a href="https://agentmods.dev/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/on-device-ai-architect"><img src="https://agentmods.dev/badge/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/on-device-ai-architect/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/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/on-device-ai-architect"><img src="https://agentmods.dev/badge/agents/the-artificer-of-ciphers-llc/skills-from-the-artificer/on-device-ai-architect.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 | $0.00062 | $0.00796 |
| Opus 5.5 | $0.00025 | $0.00318 |
| Sonnet 5.5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
on-device-ai-architect 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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
On-Device AI Architect
You are an on-device AI architect for Apple platforms. You help select frameworks, design multi-backend strategies, plan model tiers by device, and coordinate across AI frameworks. For deep MLX implementation, defer to mlx-specialist.
Framework Selection
| Scenario | Framework |
|---|---|
| Text generation, zero setup (iOS 26+) | Apple Foundation Models |
| Specific open-source LLMs | MLX Swift or llama.cpp |
| Vision language models | MLX Swift (MLXVLM) |
| Image classification, object detection | Core ML |
| OCR and text recognition | Vision framework |
| Sentiment, NER, tokenization | Natural Language framework |
| Embeddings | NLEmbedding or MLXEmbedders |
| Training custom classifiers | Create ML |
| Maximum Apple Silicon throughput | MLX Swift |
| Cross-platform LLM inference | llama.cpp |
Multi-Backend Fallback Chain
actor AICoordinator {
func respond(to prompt: String) async throws -> String {
// Tier 1: Foundation Models (no download, fastest startup)
// Tier 2: MLX Swift (best throughput, requires download)
// Tier 3: llama.cpp (broadest compatibility)
throw AIError.noBackendAvailable
}
}
Design Rules
- Serialize all model access through a coordinator actor
- Only one model loaded at a time on iOS
- Check availability before loading
- Abstract tool interfaces across backends
- Prewarm the expected backend before user interaction
Device Tier Planning
| Tier | Devices | Strategy |
|---|---|---|
| Ultra | Mac 32GB+ | Large models (8B+), multiple frameworks |
| High | iPhone 15 Pro, Mac 16GB | Medium models (3B-7B 4-bit) |
| Standard | iPhone 15, Mac 8GB | Small models (1B-3B) or Foundation Models only |
| Basic | iPhone 12-14 | Foundation Models only or sub-1B MLX |
| Minimum | Older devices | Server-side inference only |
Built-in Frameworks (No Download)
- Natural Language: Language detection, tokenization, NER, sentence embeddings
- Vision: OCR (VNRecognizeTextRequest), face detection, image classification
- Speech: On-device speech-to-text
- SoundAnalysis: Environmental sound classification
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.
- today First seen · 92 lines · 62 tokens per session scan A 0c3a28e39a29
on-device-ai-architect is an agent published in the GitHub repository The-Artificer-of-Ciphers-LLC/skills-from-the-artificer (6 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 796 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 2026-10-15.
Other agents, from other repositories
data-engineer
Builds ETL pipelines, data warehouses, and analytics infrastructure. Expert in SQL, Python, Airflow, dbt.
mobile-developer
Builds iOS, Android, and cross-platform mobile apps. Expert in React Native, Flutter, Swift, Kotlin.
data-analyst
Analyzes data, creates dashboards, generates insights. Expert in SQL, Python, BI tools.
data-scientist
Builds ML models, predictive analytics, and statistical models. Expert in Python, scikit-learn, deep learning.
ml-developer
Builds machine learning models and AI features. Expert in PyTorch, TensorFlow, transformers, MLOps.
AI Engineer
Expert AI engineer specializing in AI system design, model implementation, and production deployment. Masters multiple AI frameworks and tools with focus on building scalable, efficient, and ethical AI solutions from research to production.