principle-build-the-leverlisted

# Build the Lever When the work isn't trivial, build the tool that does it instead of doing it by hand. **Why:** Two payoffs. Throughput: a codemod, generator, or script does the work the same way every time and reruns for free. Confidence: the tool is one artifact a reviewer can read and rerun to check the work. Hand-done changes can only be re-verified by redoing them. A deterministic script turns "trust me" into "run this". **Pattern:** Default to building the lever. Skip it only when the task is genuinely trivial, a couple of obvious edits you can see at a glance. - Do the first unit by hand to learn the recipe, then build the tool. Prove it by rerunning it on that unit and diffing against your hand-done version. Make the lever safe to rerun. A reviewer will. - Codemod or script for edits, generator for repetitive files, a dump-to-sqlite query for analysis, a rerunnable check for verification. - A deterministic lever beats fan-out. If the tool can process every unit in one pass, run it yourself; don't fan out delegates to hand-apply what a script can do. - When independent work passes [`../david-mode/references/agent-runtime.md`](../david-mode/references/agent-runtime.md), put its shared recipe, verification contract, and write fences in one named file. The parent owns that file and dispatch; workers read it without changing the contract. Create a reusable skill only when the recipe will outlive this run. - Applying this principle produces a reusable artifact: a codem