principle-build-the-lever

Guides building rerunnable codemods, scripts, and generators instead of manual edits.

Updated Jul 29, 2026
One-click install
npx skills add https://github.com/mmdmcy/fluttAIrbar --skill principle-build-the-lever-mmdmcy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-build-the-lever
Source: https://github.com/mmdmcy/fluttAIrbar/tree/main/plugins/pstack/skills/principle-build-the-lever
Command: npx skills add https://github.com/mmdmcy/fluttAIrbar --skill principle-build-the-lever-mmdmcy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Hand-done edits, migrations, and analyses cannot be re-verified without redoing them, forcing reviewers to trust the author instead of checking the work. This Skill instructs the agent to build a deterministic tool that performs or proves the work, turning "trust me" into "run this". ## Core Features & Use Cases - Lever-First Workflow: Do the first unit by hand to learn the recipe, then build a codemod, script, or generator and prove it by diffing against the hand-done version. - Deterministic Over Fan-Out: Prefer a single-pass tool over delegating repetitive hand-application to subagents; when delegating, write the recipe as a shared skill outside the delegates' write scope. - Reviewable Artifacts: Produce a committed, rerunnable artifact (codemod, generator, sqlite dump query, or verification check) that reviewers can rerun to validate the work. - Use Case: When migrating hundreds of files to a new API, write a codemod, verify it against one hand-edited file, run it across the codebase, and commit the script so the migration can be rerun later. ## Quick Start Apply the build-the-lever principle to this migration task by writing a rerunnable codemod 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 across many files?▼

Do the first file by hand to learn the recipe, then write a codemod or script that applies the same transformation. Verify it by rerunning on the hand-edited file and diffing the outputs, then run it across all remaining files.

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

Build a tool whenever the work is non-trivial, including edits, migrations, analyses, and checks. Skip the tool only for genuinely trivial tasks, meaning a couple of obvious edits you can verify at a glance.

Should I delegate repetitive edits to subagents or write a script?▼

A deterministic lever beats fan-out: if a script can process every unit in one pass, run it yourself rather than delegating hand-application. When delegation is necessary, write the recipe as a shared skill all subagents read, kept outside their write scope.

How do I make automated changes reviewable by teammates?▼

Produce a rerunnable artifact such as a codemod, generator, or verification check and commit it with the change. Reviewers can then rerun the tool to confirm the work instead of re-verifying each edit by hand.

What are the limitations of the build-the-lever approach?▼

The principle warns against over-engineering: build the smallest script that does or proves the job, never a framework. It also does not apply to trivial edits where a tool would cost more than the work itself.