edge-inference

edge-inference is a skill for Claude Code from claude-dev-suite/claude-dev-suite. It costs 163 tokens per session (662 once invoked), scanned A, original, MIT.

A guide to designing AI that runs directly on devices such as microcontrollers, phones, NPUs, and small computers. It covers model size, reduced-precision formats, memory, energy use, and response time.

In plain words
What is it for?
Planning on-device AI systems, choosing hardware and models, sizing memory and energy budgets, and evaluating quantization for TinyML or edge devices.
Why use it?
It helps you decide whether AI should run on the device or in the cloud and whether the available hardware can handle the model. It also explains the trade-off between smaller, faster models and accuracy.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Install

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.

agentmods
npx agentmods add skills/claude-dev-suite/claude-dev-suite/edge-inference
Any agent
npx skills add claude-dev-suite/claude-dev-suite --skill edge-inference
Clone the repo
git clone --depth 1 https://github.com/claude-dev-suite/claude-dev-suite

Made for: Claude Code.

Wrote 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.

agentmods badge for edge-inference

README.md
[![agentmods](https://agentmods.dev/badge/skills/claude-dev-suite/claude-dev-suite/edge-inference.svg)](https://agentmods.dev/skills/claude-dev-suite/claude-dev-suite/edge-inference)
Your own site
<a href="https://agentmods.dev/skills/claude-dev-suite/claude-dev-suite/edge-inference"><img src="https://agentmods.dev/badge/skills/claude-dev-suite/claude-dev-suite/edge-inference.svg" alt="Measured on agentmods" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00163 $0.00662
Opus 5 $0.00081 $0.00331
Sonnet 5 $0.00033 $0.00132
Haiku 4.5 $0.00016 $0.00066

Measured 6d ago against content hash 17f0a4fb7397, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

edge-inference 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 6d 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.

skills/ai-systems/edge-inference/SKILL.md · 48 lines

What it actually says

Edge / On-Device Inference

Why on-device (the decision drivers)

  • Latency: on-device token/inference in ~tens of ms vs 200–500ms cloud round-trip — decisive for voice, AR, control loops.
  • Privacy / offline / cost: data never leaves the device; works without connectivity; no per-call cloud cost.
  • Cost of doing it: tight memory/energy/thermal budgets; smaller models; more engineering.

The hardware tiers (match model to silicon)

Tier Silicon Typical model
MCU / TinyML Cortex-M + tiny NPU (sub-$1 class) KB-MB models: keyword spotting, anomaly detection (TFLite Micro)
Mobile / AI-PC Phone NPU, laptop NPU (tens of TOPS) Quantized 3–8B LLMs, vision
Edge box Jetson Orin/Thor, Coral, Hailo (40+ TOPS) 7–13B LLMs, multi-camera vision

Architectural levers

  • Quantization is the key enabler: FP16 → INT8 → INT4 trades accuracy for memory/throughput/energy. Most edge LLMs run INT4/INT8. Validate accuracy loss.
  • Model choice: small instruct/distilled models (e.g. 3–8B class) and vision models sized to the NPU's memory bandwidth, not just TOPS.
  • Runtime: TFLite/LiteRT, ONNX Runtime, ExecuTorch, llama.cpp/Ollama, vendor SDKs (TensorRT for Jetson). Pick what targets the accelerator.
  • Budgets: state the TOPS, RAM, and energy-per-inference budget up front — they bound everything. Batch=1, KV-cache memory dominates LLM RAM.

When to recommend edge vs cloud vs hybrid

  • Hard latency / offline / privacy / per-unit cost → on-device.
  • Large model / variable load / centralized updates → cloud serving.
  • Both needs → hybrid (small local model + cloud escalation): see hybrid-edge-cloud.
Changes

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.

  1. 6d ago First seen · 48 lines · 163 tokens per session scan A 17f0a4fb7397

Subscribe to this mod's changes

edge-inference is a skill published in the GitHub repository claude-dev-suite/claude-dev-suite (30 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 662 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens