ollama

ollama is a command for coding agents from gopherguides/gopher-ai. It costs 13 tokens per session (1,521 once invoked), scanned A, original, MIT.

A command for sending prompts to AI models running locally through Ollama, a tool that runs models on your own computer. It uses an installed local model and keeps your data on the machine.

In plain words
What is it for?
Use it to review or explain code, suggest Go coding practices, and look for security issues. Run it with a prompt such as “review this authentication code.”
Why use it?
It lets you ask for code help without sending your code to an external service. It also avoids confusion about which local model to use.

Command

Part of the llm-tools plugin — 2 skills, 7 commands shipped together

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 commands/gopherguides/gopher-ai/ollama
Clone the repo
git clone --depth 1 https://github.com/gopherguides/gopher-ai

Or install llm-tools, the plugin that ships this one along with the rest of its 2 skills, 7 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/gopherguides/gopher-ai/ollama.svg)](https://agentmods.dev/commands/gopherguides/gopher-ai/ollama)
Your own site
<a href="https://agentmods.dev/commands/gopherguides/gopher-ai/ollama"><img src="https://agentmods.dev/badge/commands/gopherguides/gopher-ai/ollama.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,521 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 $0.00013 $0.01521
Opus 5 $0.00006 $0.00760
Sonnet 5 $0.00003 $0.00304
Haiku 4.5 $0.00001 $0.00152

Measured 4d ago against content hash 096cb433b9e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ollama 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 4d 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.

plugins/llm-tools/commands/ollama.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Local Models via Ollama

If $ARGUMENTS is empty or not provided:

Display usage information and ask for input:

This command runs prompts through local models via Ollama. Your data stays on your machine.

Usage: /ollama <prompt>

Examples:

Command Description
/ollama review this authentication code Code review
/ollama explain this concurrent pattern Code explanation
/ollama suggest Go idioms for this function Best practices
/ollama what security issues do you see Security analysis

Model choice is based on what is installed locally. When running a prompt, first call ollama list, prefer the first installed model whose name contains code or coder, and fall back to the first installed model. If no models are installed, offer pull suggestions such as qwen3-coder, qwen2.5-coder, or deepseek-coder-v2 as examples only.

Privacy Note: All processing happens locally. Your code never leaves your machine.

Ask the user: "What would you like to analyze locally?"


If $ARGUMENTS is provided:

Run a task using Ollama with the prompt: $ARGUMENTS

1. Check Prerequisites

First, check if Ollama is installed:

which ollama

If not found, inform the user:

Ollama is not installed. Install it with:

brew install ollama

Or visit: https://ollama.ai

Then ask if they want to proceed after installation or use /codex or /gemini instead.

2. Check if Ollama is Running

ollama ps 2>/dev/null

If not running or errors, offer to start it:

Ollama server is not running. Would you like me to start it?

If yes:

ollama serve &
sleep 2

3. List Available Models

ollama list

Show the user which models are already downloaded. Use the first column (NAME) as the installed model list, excluding the header row.

4. Select Model

Build the model menu from the actual ollama list output, not from a static table.

Read the full file on GitHub · 237 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.

  1. 4d ago First seen · 237 lines · 13 tokens per session scan A 096cb433b9e4

Subscribe to this mod's changes

ollama is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,521 once invoked, about $0.0001 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.