Darwin — Development agent for Claude Code
Extract durable, investment-relevant mental models and concepts from reviewed source notes into linked concept notes.
How to install Darwin
Installs to ~/.claude/agents/migchw-llm-wiki-starter-darwin.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Migchw/llm-wiki-starter/HEAD/.claude/agents/darwin.md -o ~/.claude/agents/migchw-llm-wiki-starter-darwin.md Restart Claude Code, or start a new session, for it to be picked up.
What Darwin does
name: darwin description: Extract durable, investment-relevant mental models and concepts from reviewed source notes into linked concept notes. Use only after evidence and review gates are complete. effort: medium
Darwin — Investment Concept Extractor
Read `.agents/AGENTS.md`, `04-Schema/Concept Checklist.md`, reviewed source notes, and existing concepts before creating or updating anything.
Purpose & Persona
Darwin transforms raw factual events and technical details into **dura
Alternatives in Development
- Gitnexus Docs Dod Reviewer — GitNexus docs and Definition-of-Done reviewer 45.8k ★
- Cross Linker — Scan recent or specified notes for missing wikilinks 4.6k ★
- Chronicler — You are a specialized session analyst 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Leopold
Drafts and updates Investment Thesis notes (04-Schema/Templates/Thesis.md) by synthesizing existing reviewed C
Professor
Academic teaching specialist — explains concepts at the right level, builds mental models, designs exercises
Codebase Mental Model Documenter
Use this agent when you need to create or update technical documentation that helps developers understand the
Founder Coach
Executive coach for startup founders. Focuses on mental models, prioritization, leadership challenges, and avo
Ix System Explorer
Builds a complete architectural mental model of a codebase or subsystem. Use when you need to orient in an unf
Concept Explainer
Use this agent when you need clear, comprehensive explanations of code functionality, programming concepts, sy
Related Skills
Vault Teacher
Explain a vault note using its linked concepts and neighboring knowledge. Use when the user wants a contextual
Darwin Agents
AI agents that improve themselves. Self-evolving prompts via A/B testing, multi-model critics, and safety gate
Roadmap Pro
Shape evidence-linked backlog choices, advise on priorities, reconcile human selection, explain every reviewed