Generate a branded HTML accountability tracker for the next N days using the "Define Done" ritual. Takes 3 outcomes per day max (binary, shippable, no fluff), applies Walid's prompting principles for Claude Code, and outputs a self-contained HTML file ready to pin in a browser tab. Use when the user says "define…
Complete reference for choosing and operating parallel execution primitives in Claude Code. Use when deciding whether to spawn subagents, forks, workflows, or teams — and how to steer, observe, and resume them. Also covers inheritance model, token budget routing, and reprompting running agents.
How an agent should reason about what it has, what it can do, what to delegate, and how to verify without assumptions. Read before starting any non-trivial autonomous task. Covers self-inventory, verification levels, assumption audit, and when to stop and escalate.
Native Claude Code capabilities most people never discover. Quick pick table + pointers to reference files. Read this first — pull reference files only when you need the full detail on a specific capability.