ollama Repository Analysis Prompt

repo analysisvery high Token Costadvanced

Prompt provenance

Inspired by ollama/ollama.

Reverse-engineered from real GitHub workflow.

Updated 2 weeks ago·0 copies

Reverse-engineer a local LLM runtime by tracing CLI commands, server startup, API routes, model loading, scheduler behavior, runner processes, environment configuration, and coding-agent integration risks.

What this solves

Local LLM runtime architecture review

Best used when

You need to understand how a local LLM runtime starts, serves API requests, loads models, and manages runner processes.
You are reviewing local-model support for AI coding agents, IDE integrations, or self-hosted LLM workflows.
You want a source-grounded checklist for model storage, GPU scheduling, environment configuration, API compatibility, and cloud/local boundary risks.

Avoid using when

You only need user-facing installation instructions for a local LLM tool.
You are reviewing a hosted-only LLM gateway with no local model lifecycle or runner process.
You want to publish production prompt rows directly without maintainer review.

Prompt Variants

Use this when Claude has broad repo-reading access and should produce a structured architecture review of a local LLM runtime with explicit file evidence.