agentleFS
Sign inStart free
3metaJun3metaJun/mstack/skills/principle-build-the-lever/SKILL.md

principle-build-the-lever

Skill0 starsChanged 27 days agoMITView on GitHub

For repeated, bulk, or mechanically consistent edits, migrations, analyses, and checks, build the smallest rerunnable codemod, script, generator, or shared workflow when its reuse or proof value exceeds its cost.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When repeated or mechanically consistent work would be safer or faster through a tool, build the smallest one that does it or proves it.

    line 9
  2. Distinctive:

    Run it against the learned unit and compare the result with the manual version.

    line 16
  3. Distinctive:

    Use it for the remaining units and retain the verification output.

    line 17
  4. Distinctive:

    Prefer a lever over parallel manual edits when one deterministic pass can own the entire operation.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build the lever

When repeated or mechanically consistent work would be safer or faster through a tool, build the smallest one that does it or proves it. Do not build a tool for a complex one-off when direct work is clearer and equally verifiable.

  1. Perform one representative unit manually to learn the recipe.
  2. Encode that recipe in a codemod, script, generator, query, or shared skill.
  3. Make the tool safe to rerun.
  4. Run it against the learned unit and compare the result with the manual version.
  5. Use it for the remaining units and retain the verification output.

A deterministic lever improves both throughput and confidence. A reviewer can read and rerun one artifact instead of reproducing many manual steps.

Prefer a lever over parallel manual edits when one deterministic pass can own the entire operation. If work must be delegated, give every worker the same read-only workflow and non-overlapping file ownership so instructions and edits do not drift.

Applying this principle should produce an artifact. If there is no script, generator, query, codemod, or shared workflow to inspect, the lever was not built. Keep it small and commit it when the task will outlive the session.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free