Playbooks

Tactical guides for building with AI

Free, step-by-step guides to the unglamorous side of the work: keeping the bill down, running open models, sending each task to the model that earns it. Tools and prices age fast, so every playbook shows the date it was last verified.

Every guide runs its demos right here: animated terminal sessions and Claude Code walkthroughs, no sign-up needed.

10 minVerified June 29, 2026

Build in Claude Code without the surprise bill

Five small habits that keep your AI spend low, shown as the exact things you type. No code, no jargon.

costclaude-codeautomationsbeginner

14 minVerified June 30, 2026

Run Claude Code on open-source models via OpenRouter

Point the Claude Code harness at GLM and other open models through OpenRouter, step by step, and know when it is worth it.

claude-codeopenrouteropen-sourceglmvscode

12 minVerified June 30, 2026

Run Claude Code directly on GLM, Kimi, or DeepSeek

Skip the middleman. Point Claude Code straight at a provider's own endpoint for the lowest price, often a flat coding plan, with the trade-offs mapped.

claude-codeopen-sourcedeepseekglmkimivscodedirect

15 minVerified June 30, 2026

Route each task to the cheapest model that can do it

Send the grunt work to a cheap open model and keep the hard thinking on Claude, automatically, with one small local router.

claude-codeopen-sourceroutingopenrouterhybridvscode

Premium15 minVerified June 29, 2026

Keep long agent runs from blowing the context window

Compaction, context editing, and memory: when to reach for each so a long-running agent stays coherent and cheap.

agentscontextclaude-code

Premium playbooks open with the melwyn Class premium tier. Each one carries its own waitlist form.