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 you fan work out to subagents, write the lever as a skill they all read: the recipe, the verification contract, and the do-not-touch fences in one artifact, so every delegate inherits the same hardened version instead of re-explaining it per prompt and watching each one drift. Keep it outside the delegates' write scope so they can't quietly edit the contract.
- Applying this principle produces a file. If you cited it and there is no codemod, script, generator, or delegate skill in the diff, you didn't apply it.
- Commit the lever when the work outlives the session, so the next run reruns it instead of redoing it.
Balance: The bar is triviality, not repetition. A one-off still earns a lever when the lever is what makes the work checkable. Per the Laziness Protocol, build the smallest script that does or proves the job, never a framework.
Battle-tested: A recurring babysit loop hand-classified the same handful of conflict shapes ("duplicate-import, trivial," "stale-title fix") for roughly 20 rounds before admitting "I don't have a mechanical fix for that." The loop's cadence was itself a lever, but the per-round classification inside it stayed manual pattern-matching the whole time, never promoted to a script — even though the same babysitting task eventually produced an unrelated reusable skill. Watch for this specifically: a /loop-style rerun that keeps re-deriving the same verdict round after round is the lever that didn't get built. If you cited this skill and a PR body references it with no script in the diff, that's the tell.
Distinct from Encode Lessons in Structure, which makes a recurring instruction a durable guardrail. This is throughput and reviewability on the work in front of you. For scripting the verification itself, see the Prove It Works principle (not yet written as a skill).
1---2name: principle-build-the-lever3description: Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.4---5# Build the Lever67When the work isn't trivial, build the tool that does it instead of doing it by hand.89**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".1011**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.1213- 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.14- Codemod or script for edits, generator for repetitive files, a dump-to-sqlite query for analysis, a rerunnable check for verification.15- 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.16- When you fan work out to subagents, write the lever as a skill they all read: the recipe, the verification contract, and the do-not-touch fences in one artifact, so every delegate inherits the same hardened version instead of re-explaining it per prompt and watching each one drift. Keep it outside the delegates' write scope so they can't quietly edit the contract.17- Applying this principle produces a file. If you cited it and there is no codemod, script, generator, or delegate skill in the diff, you didn't apply it.18- Commit the lever when the work outlives the session, so the next run reruns it instead of redoing it.1920**Balance:** The bar is triviality, not repetition. A one-off still earns a lever when the lever is what makes the work checkable. Per the [Laziness Protocol](../principle-laziness-protocol/SKILL.md), build the smallest script that does or proves the job, never a framework.2122**Battle-tested:** A recurring babysit loop hand-classified the same handful of conflict shapes ("duplicate-import, trivial," "stale-title fix") for roughly 20 rounds before admitting "I don't have a mechanical fix for that." The loop's cadence was itself a lever, but the per-round classification inside it stayed manual pattern-matching the whole time, never promoted to a script — even though the same babysitting task eventually produced an unrelated reusable skill. Watch for this specifically: a `/loop`-style rerun that keeps re-deriving the same verdict round after round is the lever that didn't get built. If you cited this skill and a PR body references it with no script in the diff, that's the tell.2324Distinct from [Encode Lessons in Structure](../principle-encode-lessons-in-structure/SKILL.md), which makes a recurring instruction a durable guardrail. This is throughput and reviewability on the work in front of you. For scripting the verification itself, see the Prove It Works principle (not yet written as a skill).
EdbertChan