local-llm

local-llm is a skill for Claude Code from jimmc414/claude-code-plugin-marketplace. It costs 97 tokens per session (1,928 once invoked), scanned B, original, MIT.

Guidance for running and managing AI language models locally with Ollama, including model selection, GPU memory use, custom model files, and an OpenAI-compatible connection.

In plain words
What is it for?
Use it to configure Ollama, switch between faster and higher-quality models, create custom models, and connect local models to applications.
Why use it?
It helps you choose suitable models and troubleshoot local AI setups instead of guessing which model or settings to use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the local-llm plugin — 1 skill, 1 agent shipped together

Good fit Use it to configure Ollama, switch between faster and higher-quality models, create custom models, and connect local models to applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jimmc414/claude-code-plugin-marketplace/local-llm
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.

Any agent
npx skills add jimmc414/claude-code-plugin-marketplace --skill local-llm
Clone the repo
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplace

Made for: Claude Code.

Or install local-llm, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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 local-llm

README.md
[![agentmods](https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/local-llm/github.svg)](https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/local-llm)
Your own site
<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/local-llm"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/local-llm/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.

agentmods 80×15 button for local-llm

Your own site · 80×15
<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/local-llm"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/local-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,928 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00097 $0.01928
Opus 5 $0.00048 $0.00964
Sonnet 5 $0.00019 $0.00386
Haiku 4.5 $0.00010 $0.00193

Measured 9d ago against content hash 60431f65e5c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

local-llm scanned grade B with 2 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 9d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo systemctl restart ollama

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:11434/v1/models
plugins/local-llm/skills/local-llm/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local LLM Management

This skill provides comprehensive guidance for managing local LLM models via Ollama for development, testing, and production use.

Overview

Ollama provides a simple way to run large language models locally with:

  • Easy model management (pull, run, stop)
  • OpenAI-compatible API at http://localhost:11434/v1
  • GPU acceleration with automatic VRAM management
  • Custom model creation via Modelfiles

Two-Tier Model Strategy

For efficient development workflows, use a two-tier approach:

Tier Purpose Model Size Speed Use Case
Fast Iteration 3-4B params 30+ tok/s Sanity tests, CI/CD, rapid prototyping
Quality Validation 7-14B params 5-15 tok/s E2E testing, complex reasoning, final QA

Recommended Model Combinations

GPU VRAM Fast Model Quality Model
4 GB Qwen2.5 3B Q4 Phi-3 4B Q4
6 GB Qwen2.5 4B Q4 Llama 3.2 8B Q4
8 GB Llama 3.2 3B Q8 DeepSeek-R1 8B Q4
12+ GB Qwen2.5 7B Q4 Llama 3.1 14B Q4

Create custom models using the templates in templates/ directory.

Quick Reference Commands

Running Models

# Interactive chat
ollama run <model-name>

# Single prompt (non-interactive)
echo "Your prompt" | ollama run <model-name>

# With verbose output (shows speed metrics)
echo "Your prompt" | ollama run <model-name> --verbose

Model Management

# List all models
ollama list

# Check currently loaded models (VRAM usage)
ollama ps

# Unload model to free VRAM
ollama stop <model-name>

# View model details
ollama show <model-name>

# View Modelfile configuration
ollama show <model-name> --modelfile

# Delete a model
ollama rm <model-name>

# Pull/update a model
ollama pull <model-name>

Service Management

# Check Ollama service status
systemctl status ollama

# Restart Ollama service
sudo systemctl restart ollama

# View Ollama logs
journalctl -u ollama -f

# Manual start (if service not running)
ollama serve

Read the full file on GitHub · 266 lines

Files

What ships with it

8 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.

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. 9d ago First seen · 266 lines · 97 tokens per session scan B 60431f65e5c5

Subscribe to this mod's changes

local-llm is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,928 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

generate

Build a source-backed AI industry briefing from official vendor publications, configured RSS feeds, GitHub releases, reputable secondary reporting, and user-supplied URLs. Use when: 'ai briefing', 'ai news', 'what's new in AI', 'catch me up on AI', 'prep for AI meeting', 'AI roundup', or 'generate AI slides'.

melodic-software/claude-code-plugins · 72 tokens

design

Design an evaluation suite for an LLM-based application or a Claude Code skill: interview for measurable success criteria, pick a grading method per criterion, and scaffold a criteria doc plus eval cases into the consumer repo. Use when: 'design evals', 'create an eval suite', 'scaffold evals', 'write evals for my…

melodic-software/claude-code-plugins · 141 tokens

methodology

Answers LLM-evaluation design questions from Anthropic's official evaluation guidance — success criteria, eval-suite design, and grading methods for LLM-based applications and Claude Code skills. Use when: 'define success criteria', 'how do I eval this', 'LLM eval', 'measure prompt quality', 'LLM judge', 'model-graded…

melodic-software/claude-code-plugins · 144 tokens

ai-policy-generator

AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.

travisjneuman/.claude · 42 tokens

data-engineering

ETL/ELT pipelines, data warehousing (BigQuery, Snowflake, Redshift), stream processing (Kafka, Spark Streaming), orchestration (Airflow, Dagster, Prefect), dbt transformations, and data lake architecture. Use when building data pipelines, designing warehouse schemas, or implementing real-time data processing.

travisjneuman/.claude · 70 tokens

audit-progressive-disclosure

Read-only progressive-disclosure audit for agent-facing instruction markdown. Grades every target against a three-tier load-cost model (always-loaded / invocation-loaded / on-demand) and classifies seven finding shapes in two lanes: split opportunities (oversize vs tier-calibrated Anthropic-prescribed caps…

melodic-software/claude-code-plugins · 259 tokens