ollama_manager

ollama_manager is a skill for Claude Code, Codex from tubecreate/tubecli. It costs 0 tokens per session (403 once invoked), scanned A, original, MIT.

A manager for Ollama, a local program that runs AI models on your own computer. It lets agents check the server, install or remove models, inspect them, see which are running, and assign them to agents.

In plain words
What is it for?
Checking Ollama, listing and inspecting models, downloading or removing models, viewing running models, and assigning a local model to an agent.
Why use it?
It lets you use local AI models without cloud API keys. Centralising model management makes it easier to see what is installed and choose which model an agent should use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Checking Ollama, listing and inspecting models, downloading or removing models, viewing running models, and assigning a local model to an agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tubecreate/tubecli/ollama_manager
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 tubecreate/tubecli --skill ollama_manager
Clone the repo
git clone --depth 1 https://github.com/tubecreate/tubecli

Made for: Claude Code, Codex.

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 ollama_manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/tubecreate/tubecli/ollama_manager/github.svg)](https://agentmods.dev/skills/tubecreate/tubecli/ollama_manager)
Your own site
<a href="https://agentmods.dev/skills/tubecreate/tubecli/ollama_manager"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/ollama_manager/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 ollama_manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/tubecreate/tubecli/ollama_manager"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/ollama_manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00403
Opus 5 $0.00000 $0.00201
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00040

Measured 12d ago against content hash 958b71d43b47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ollama_manager 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (__init__.py, commands.py, extension.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tubecli/extensions/ollama_manager/SKILL.md · 57 lines

What it actually says

Ollama Local Model Manager — AI Skill Guide

Extension: ollama

Manages local Ollama AI models for agents to use without cloud API keys.

Available Commands

Server Status

tubecli ollama status

List Models

tubecli ollama models

Pull Model

tubecli ollama pull qwen:latest
tubecli ollama pull llama3:8b
tubecli ollama pull gemma2:9b

Remove Model

tubecli ollama remove qwen:latest

Show Model Details

tubecli ollama show qwen:latest

List Running Models

tubecli ollama running

API Endpoints

Method Endpoint Description
GET /api/v1/ollama/status Server status
GET /api/v1/ollama/models List models
GET /api/v1/ollama/running List loaded models
POST /api/v1/ollama/pull Pull model
DELETE /api/v1/ollama/models Remove model
GET /api/v1/ollama/models/{name} Model details
POST /api/v1/ollama/assign Assign model to agent

AI Usage

  1. Check if Ollama is running: GET /api/v1/ollama/status
  2. List available models: GET /api/v1/ollama/models
  3. If needed model not installed, pull it: POST /api/v1/ollama/pull {"model": "qwen:latest"}
  4. Assign to agent: POST /api/v1/ollama/assign {"agent_id": "...", "model": "qwen:latest"}
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. 12d ago First seen · 57 lines · 0 tokens per session scan A 958b71d43b47

Subscribe to this mod's changes

ollama_manager is a skill published in the GitHub repository tubecreate/tubecli (167 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 403 tokens. 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.