# Ollama

> Delegates an explicit analysis, review, or second-opinion request after checking the configured Ollama endpoint and requiring consent for non-loopback destinations. Use only when the user asks for Ollama; do not start a server or download a model without consent.

- Skill: `gopherguides/ollama` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add gopherguides/ollama`
- Raw SKILL.md: https://api.skillmd.com/api/skills/gopherguides/ollama/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: gopherguides (https://skillmd.com/u/gopherguides)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/gopherguides/ollama

---


# Ollama

## Plugin Resource Resolution

`<PLUGIN_ROOT>` is notation. Replace it with a concrete absolute plugin root
before every resource read or command:

- **Codex:** Start from the directory containing the absolute selected
  `SKILL.md` path, then ascend two directories (`skills/<name>` to plugin root).
- **Claude Code:** Bind it to the injected `${CLAUDE_PLUGIN_ROOT}` value.

Read both files completely, then apply the adapter while following the command
body:

1. `<PLUGIN_ROOT>/lib/codex-command-adapter.md`
2. `<PLUGIN_ROOT>/commands/ollama.md`