principle-build-the-lever

Builds rerunnable codemods, scripts, and generators instead of performing edits by hand.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/jeremybrasher/grokbot-skills --skill principle-build-the-lever-jeremybrasher
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-build-the-lever
Source: https://github.com/jeremybrasher/grokbot-skills/tree/main/collections/pstack/skills/principle-build-the-lever
Command: npx skills add https://github.com/jeremybrasher/grokbot-skills --skill principle-build-the-lever-jeremybrasher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Hand-applied edits, migrations, and checks cannot be re-verified without redoing the work, leaving reviewers with nothing to rerun. This Skill replaces manual work with a deterministic tool — a codemod, script, generator, or delegate skill — that a reviewer can execute to confirm the result. ## Core Features & Use Cases - Lever-First Workflow: Do the first unit by hand to learn the recipe, then build a tool that reproduces it and diff the outputs to prove correctness. - Deterministic Over Fan-Out: Prefer a single script that processes every unit over delegating hand-applied changes to subagents; when delegating, ship the recipe as a skill outside the delegates' write scope. - Intake and HOLD Gates: Stop and name the gap when the trigger, situation object, or decision to change is missing, rather than citing the principle decoratively. - Use Case: During a codebase-wide migration, write a codemod that performs the transformation, rerun it on a hand-edited sample to verify, and commit the script so reviewers can rerun it. ## Quick Start Apply the build-the-lever principle to this migration task and produce a rerunnable script instead of editing each file by hand.

Frequently Asked Questions about principle-build-the-lever

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate repetitive code edits with a codemod?▼

Do the first unit by hand to learn the recipe, then write a codemod or script that reproduces it. Verify by rerunning the tool on that unit and diffing against your hand-done version, and make the tool safe to rerun.

When should I write a script instead of editing files manually?▼

Write a script whenever the work is non-trivial, including one-off tasks where the script is what makes the work checkable. Skip the tool only for trivial changes you can verify at a glance.

Should I use subagents or a script for bulk code changes?▼

Prefer a deterministic script that processes every unit in one pass over fanning out subagents to hand-apply changes. When delegation is necessary, write the recipe as a skill file outside the delegates' write scope.

When should I not apply the build-the-lever principle?▼

Skip it for trivial edits visible at a glance, when a narrower operational skill covers the decision, or when citing it would not change any choice. The skill also holds when the trigger, situation object, or decision to change is missing.

How do I verify a migration script produced correct results?▼

Rerun the tool on a unit you previously edited by hand and diff the two outputs. The tool itself is the reviewable artifact, so commit it when the work outlives the session.