Agent skill

Local LLM Router

by hoodini in hoodini/ai-agents-skills

Route AI coding queries to local LLMs in air-gapped networks.

No licenceAuto-check passedAI & LLM Engineering

Install Local LLM Router

skills CLI
$ npx skills add hoodini/ai-agents-skills --skill local-llm-router -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hoodini/ai-agents-skills local-llm-router --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hoodini/ai-agents-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/local-llm-router .claude/skills/local-llm-router && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
local-llm-router
GitHub stars
282
Token cost
~20k tokens
SKILL.md length
272 words
Files
2 (incl. references)
Skills in repo
32
Repo updated
First seen
Licence
None found

At a glance

Route AI coding queries to local LLMs in air-gapped networks.

  • Works in 2 steps: Serena MCP Server installed and running… → At least one local LLM service running…
  • Working offline
  • SKILL.md covers Prerequisites (CRITICAL), Quick Start, Serena Integration (PRIMARY… and Service Discovery, plus 9 more sections
  • Calls curl, pip and uvx; reaches github.com

What it does

Local LLM Router is an agent skill from hoodini/ai-agents-skills. Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan, OpenWebUI), or in secure/closed environments. Triggers on local LLM, Ollama, LM Studio, Jan, air-gapped, offline AI, Serena, local inference, closed network, model routing, defense network, secure coding.

Its SKILL.md is about 20k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/model-matrix.md`).

It sits in AI & LLM Engineering, covering LLM inference and serving, Model routing and gateways and Secure coding. It works with Model Context Protocol and Ollama. The repository describes itself as: 🧠 AI Agent Skills Repository - A curated collection of specialized skills for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf). Created by Yuval Avidani using…

When your agent uses it

  • Working offline
  • With local models (Ollama
  • In secure/closed environments
  • Local inference

Example prompts

  • “/local-llm-router”

Requirements

  • Python 3
  • Docker

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Serena MCP Server installed and running (PRIMARY TOOL)
  2. At least one local LLM service running (Ollama, LM Studio, Jan, etc.)

What it can do on your machine

Read from SKILL.md and the folder at commit f7a43d8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • pip
    • uvx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • lmstudio.ai
    • jan.ai
    • docs.openwebui.com
    • localai.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Local LLM Router loads about 20k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 272 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~20k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 272 words (~20,121 tokens).

“Intelligent routing of AI coding queries to local LLMs with Serena LSP integration for secure, offline-capable development environments.”

— opening of SKILL.md by hoodini
name
local-llm-router

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in skills/local-llm-router of hoodini/ai-agents-skills.

  • SKILL.md
  • references/model-matrix.md

Open the folder on GitHubat commit f7a43d8

Compare with similar skills

Local LLM Router next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Local LLM Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local LLM Router this skillhoodini/ai-agents-skills282—~20kAutomated safety check: PassNone
Perfupraullenchai/Rapid-MLX4k—~1.6kAutomated safety check: NotesCustom licence
Integrate Modeltryonlabs/opentryon551—~1.1kAutomated safety check: PassCustom licence
Agent Frameworkjihadkhawaja/Egroo178—~1.9kAutomated safety check: PassApache-2.0
Pixiu LLM Gatewayapache/dubbo-go-pixiu567—~2.5kAutomated safety check: PassApache-2.0
New Providerfinch-xu/cc-router277—~1.6kAutomated safety check: PassMIT

Similar skills

  • Perfup

    raullenchai/Rapid-MLX

    Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

    4k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Integrate Model

    tryonlabs/opentryon

    Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).

    551 GitHub stars~1.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Agent Framework

    jihadkhawaja/Egroo

    Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).

    178 GitHub stars~1.9k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed
  • Pixiu LLM Gateway

    apache/dubbo-go-pixiu

    Creates and validates dubbo-go-pixiu LLM gateway conf.yaml. An agent skill from apache/dubbo-go-pixiu.

    567 GitHub stars~2.5k tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check passed
  • New Provider

    finch-xu/cc-router

    用于在 cc-router 仓库新增一个 LLM provider(即在 src-tauri/providers/ 下添加 YAML 描述符并完成配套的同步改动)。当用户说「加 provider」「接入 XX 厂商」「新增订阅源」「provider YAML」「让 cc-router 支持 OpenRouter/Together/Groq/Ollama 之类」时必须触发本…

    277 GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Configuring Vision

    oxbshw/watch-skill

    The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models.

    470 GitHub stars~509 tokensUpdated 26 days ago
    AI & LLM EngineeringAuto-check: notes

More from hoodini/ai-agents-skills

All 32 skills in this repo
  • Parallax Scroll-Scrub Landing Page

    hoodini/ai-agents-skills

    Turns a short video into a one-screen landing page where scrolling scrubs through the extracted frames while five text scenes crossfade over the footage.

    282 GitHub stars~3.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Yuv Viral Video

    hoodini/ai-agents-skills

    Edit any selfie or screen-share footage into a viral short-form video in YUV.AI's signature style — Apple-style liquid-glass cards (real CSS backdrop-filter), dark-mode polish, MrBeast-paced cuts…

    282 GitHub stars~7.5k tokensUpdated 3 mo ago
    Auto-check: notes
  • Meta Ads

    hoodini/ai-agents-skills

    Pull, analyze, manage, and CREATE Meta ads (Facebook, Instagram, Messenger, Threads, Click-to-WhatsApp) via the Marketing API.

    282 GitHub stars~4.2k tokensUpdated 3 mo ago
    Auto-check: notes
  • YUV Video Director

    hoodini/ai-agents-skills

    Turns an idea or script into a branded MP4 by routing each scene to HyperFrames, Lottie, Manim or GSAP, wrapping it in one brand frame file, then checking and rendering.

    282 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Video To Landing Page

    hoodini/ai-agents-skills

    Turn any video into a cinematic scroll-driven landing page — Apple-style hero where scrolling progresses the visible frame through the video.

    282 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Mermaid Diagrams

    hoodini/ai-agents-skills

    Create diagrams and visualizations using Mermaid syntax. An agent skill from hoodini/ai-agents-skills.

    282 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

Questions about Local LLM Router

What does Local LLM Router do?

Route AI coding queries to local LLMs in air-gapped networks. Local LLM Router is an agent skill from hoodini/ai-agents-skills. Route AI coding queries to local LLMs in air-gapped networks.

When should I use Local LLM Router?

Local LLM Router fits situations like: working offline; with local models (Ollama; in secure/closed environments; local inference.

How do I install Local LLM Router in Claude Code?

Run `npx skills add hoodini/ai-agents-skills --skill local-llm-router -a claude-code`. Or copy the skill folder (skills/local-llm-router in hoodini/ai-agents-skills) into .claude/skills/local-llm-router in your project. Claude Code loads it when a task matches its description.

How do I install Local LLM Router in Codex?

Run `npx skills add hoodini/ai-agents-skills --skill local-llm-router -a codex`. Or copy the skill folder (skills/local-llm-router in hoodini/ai-agents-skills) into .agents/skills/local-llm-router in your project. Codex loads it when a task matches its description.

Can I use Local LLM Router in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hoodini/ai-agents-skills --skill local-llm-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-llm-router, .gemini/skills/local-llm-router, .github/skills/local-llm-router and .opencode/skills/local-llm-router in your project.

What does Local LLM Router need to run?

Going by SKILL.md and its folder, Local LLM Router needs the command-line tools its instructions call (curl, pip and uvx). Our summary lists: Python 3; Docker.

Does Local LLM Router access the network?

SKILL.md names 5 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: lmstudio.ai, jan.ai, docs.openwebui.com and localai.io. This is read from the text; nothing was executed.

Is Local LLM Router safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Local LLM Router use?

No licence was found for Local LLM Router or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Local LLM Router use?

About 20k tokens (SKILL.md is roughly 80k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Local LLM Router?

Skills that share tags, products or a category with Local LLM Router: Perfup (raullenchai/Rapid-MLX, 4k stars), Integrate Model (tryonlabs/opentryon, 551 stars), Agent Framework (jihadkhawaja/Egroo, 178 stars) and Pixiu LLM Gateway (apache/dubbo-go-pixiu, 567 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local LLM Router?

hoodini (a GitHub user) maintains it in hoodini/ai-agents-skills, which has 282 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on July 11, 2026.

Source: hoodini/ai-agents-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.