Ollama Agent — Development agent for Claude Code
Runs a local model served by Ollama on this machine.
How to install Ollama Agent
Installs to ~/.claude/agents/wherethetunnelends-quorum-ollama-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/WhereTheTunnelEnds/quorum/HEAD/agents/ollama-agent.md -o ~/.claude/agents/wherethetunnelends-quorum-ollama-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Ollama Agent does
name: ollama-agent description: Runs a local model served by Ollama on this machine. One mode - consult (no machine access; the endpoint is a plain text-completion API with no tool loop). Use when the input must not leave the machine, when there is no network, or for bulk mechanical work where zero marginal cost matters more than depth. tools: Bash, Read, Glob, Grep model: haiku color: orange
ollama-agent
You are a bridge to a local model served by **Ollama** on this machine. You do
Alternatives in Development
- Senior Engineer P7 — P7 Senior Engineer Agent 19.5k ★
- Surveyor — You are a specialized reviewer for migrations and upgrades 3.6k ★
- Review Bugs — Reviews code changes for potential bugs found by single-threaded sequential reasoning: logic errors, null safe 432 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against
Text Slop Cleaner
This agent should be invoked to remove machine sounding text and unnecessary comments. This includes rewriting
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Ade
Agent sessions routinely outlast the machine that started them, and checking a Claude Code or Codex run from a
Document Scout
Use proactively for read-only fact-finding in local non-code documents and on the web: dates, deadlines, amoun
Metadata Extractor
Extracts paper metadata (authors, date, venue, fields, DOI/arxiv ID) and a paper-quality assessment (credibili
Related Skills
Kimi CLI Agent
Answers one council question as plain text, with no tool access.
Autopilot Nt
The executor — work a fix-workplan or prose goal to completion unattended in an isolated worktree; verify fres
Ollama Cc Plugin
Use local/cloud ollama models from Claude Code as a second engine: read-only consult/review, agentic worktree-