Skip to main content
File an issue, grab coffee, come back to a PR. Not quite there yet — but close enough to be dangerous.
The AI development surface is opinionated, not magical. Each model has a sweet spot. Each tool has a role. Universal configuration lives in one place so every IDE, every agent, every CLI reads the same rules.

The tools landscape

Model routing

Each model has a sweet spot, and work is routed to the cheapest one that can actually do it — deep reasoning and multi-file refactors to the strongest model, line-level completions to the cheap high-volume one, and anything trivial to local inference rather than burning cloud tokens. Model routing covers how that choice is made and governed: one endpoint in front of every backend, asking for a role instead of a model name, and the difference between a spend control that is enforced and one that is merely advised. Routing rules live in ~/CLAUDE.md and AGENTS.md, sourced from ai-assistant-instructions. See Repo boundaries for how rules, plugins, and docs are split across three repositories.

Repos in this section

Repo boundaries

How rules, plugins, and docs are split across three repositories.

ai-assistant-instructions

Universal AI configuration layer. Rules, permissions, workflows, agents. Loaded by every AI tool.

claude-code-plugins

Commands, skills, hooks, agents for Claude Code. Project-specific automation.

claude-code-routines

Scheduled remote-agent routines on Claude.ai. Cron-driven Claude tasks for GitHub ops.

ai-workflows

Reusable GitHub Copilot agentic workflows. Repo-level agent recipes.

raycast-smart-issue

Raycast extension. AI-drafted GitHub issues via a local MLX model.

nix-ai

The Nix package layer that ships every AI CLI to your shell.
See AI development pipeline for how these fit into the issue → PR → ship flow.