What is local-inference?

A way to run language models directly on Apple Silicon Macs through Crystal and MLX, Apple's machine-learning framework. Models can support chat, streaming text, and structured JSON output without a cloud API.

Use it for local chat, streamed responses, structured data generation, or on-device model testing on an M1-or-newer Mac.

It keeps inference on the device, avoiding a required connection to services such as OpenAI. The model can remain loaded in memory for reuse.

How crimson-knight/llamero configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to crimson-knight/llamero. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/crimson-knight/llamero/main/.claude/skills/local-inference/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/crimson-knight/llamero

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/crimson-knight/llamero/local-inference/github.svg)](https://agentmods.dev/skills/crimson-knight/llamero/local-inference)

Your own site

<a href="https://agentmods.dev/skills/crimson-knight/llamero/local-inference"><img src="https://agentmods.dev/badge/skills/crimson-knight/llamero/local-inference/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/crimson-knight/llamero/local-inference"><img src="https://agentmods.dev/badge/skills/crimson-knight/llamero/local-inference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,862 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00086	$0.02862
Opus 5.5	$0.00034	$0.01145
Sonnet 5.5	$0.00017	$0.00572
Haiku 4.5	$0.00009	$0.00286

Measured 2mo ago against content hash f93eb59352c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-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 2mo 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.

.claude/skills/local-inference/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local inference with llamero (Apple Silicon / MLX)

llamero runs language models locally on Apple Silicon through a Swift MLX bridge. The model loads into memory once and stays resident; every chat, stream, or structured call reuses it. No Python, no llama.cpp, no cloud API.

Requirements — check these first

macOS on Apple Silicon (M1 or newer). On any other platform, Llamero::Native still compiles and runs, but uses a mock bridge that returns canned text. Check at runtime with runtime.real_bridge?.
The Swift bridge dylib must be built once per machine:
```
# In a project that depends on llamero:
cd lib/llamero/native/llamero-mlx && ./build.sh
# Inside the llamero repo itself:
cd native/llamero-mlx && ./build.sh
```
build.sh installs libLlameroMLXBridge.dylib and mlx.metallib to $LLAMERO_HOME/lib when set, otherwise ~/.llamero/lib/, where llamero finds them from any project. It requires Xcode with the Metal toolchain (xcodebuild -downloadComponent MetalToolchain if the build complains about a missing metal tool).
Models download automatically from Hugging Face on first load into the configured storage root's models/ directory. The mlx-community conversions (including Gemma) are generally ungated and need no token. Gated repos (e.g. google/* originals) need HF_TOKEN set in the environment.

Storage root

Default storage is ~/.llamero. Apps that need app-owned AI data set this at boot before creating runtimes:

Llamero.storage_root = Path.home.join(".scribe")

LLAMERO_HOME=/path/to/root is the env alternative; programmatic wins. The root controls local model downloads (models/), adapter artifacts (adapters/), bridge lookup (lib/), and audio model caches (audio_models/) when audio is configured. For app-owned bridge installs, set LLAMERO_HOME when running build.sh. FluidAudio 0.15.2 still pins English Kokoro G2P assets to its own TTS cache; see development_docs/storage_configuration.md.

Read the full file on GitHub · 250 lines

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.

2mo ago First seen · 250 lines · 86 tokens per session scan A f93eb59352c4

Subscribe to this mod's changes

local-inference is a skill published in the GitHub repository crimson-knight/llamero (23 stars, last pushed 27d ago), licensed MIT. It adds 86 tokens to every session and 2,862 once invoked, about $0.0003 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 2026-08-30.

Data and AI

local-inference next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
local-inferencecrimson-knight/llamero	Skill	23	27d ago	MIT	A	86	Claude Code
agent-platform-model-registrygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	60	Claude Code, Codex
foundry-config-setupmicrosoft/agent-framework	Skill	15k	yesterday	MIT	A	65	Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills	Skill	22k	yesterday	Apache-2.0	A	132	Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	3d ago	MIT	A	35	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
finetuningmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	132	Claude Code

llamero: Skill for Claude Code