← fstackCONTENT HISTORYWHAT CHANGED · RULE-BASED ANALYSIS
Update to fstack
Snapshot Sep 30, 2026 · 23:16 UTC · version 1.1.2
Collection source: not recorded for this historical snapshot.
First saved snapshot
No earlier snapshot is available to establish a change.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "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.",
"included_files": [],
"name": "principle-build-the-lever",
"skill_md_contents": "---\r\nname: principle-build-the-lever\r\ndescription: \"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.\"\r\nuser-invocable: false\r\ndisable-model-invocation: true\r\n---\r\n# Build the Lever\r\n\r\nWhen the work isn't trivial, build the tool that does it instead of doing it by hand.\r\n\r\n**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\".\r\n\r\n**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.\r\n\r\n- 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.\r\n- Codemod or script for edits, generator for repetitive files, a dump-to-sqlite query for analysis, a rerunnable check for verification.\r\n- 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.\r\n- 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.\r\n- 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.\r\n- Commit the lever when the work outlives the session, so the next run reruns it instead of redoing it.\r\n\r\n**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.\r\n\r\nDistinct 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 [Prove It Works](../principle-prove-it-works/SKILL.md).\r\n"
}SHA-256 of public snapshot: 56f07f0592a32110feb1d2d4ad869cb1d5bdde65b382b7d210fa50bd547f1829