agentleFS
imMamdouhaboammarimMamdouhaboammar/anti-slop-engineering/skills/reduction-guard/SKILL.md

reduction-guard

Skill4 starsChanged 31 days agoMITView on GitHub

Enforce the Musk 5-Step Reduction Algorithm and 10% Add-Back Ledger calibration gate. Question requirements, delete parts before optimizing, and track deletion calibration.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Delete the part or process: Remove unused parameters, dead wrappers, and speculative branches.

    line 20
  2. Distinctive:

    Simplify or optimize: Only after deleting non-essential parts, simplify the remaining core.

    line 21
  3. Very specific:

    Every deletion and add-back is logged to .anti-slop/add-back-ledger.jsonl.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Reduction Governor & Add-Back Ledger Guard

"Possibly the most common error of a smart engineer is to optimize a thing that should not exist." — Elon Musk

Why This Skill Is Needed & Target State

AI code generators suffer from additive bias: they continuously add parameters, options, wrapper functions, and speculative configurations. When asked to optimize, they optimize dead branches rather than deleting them.

The target state is strict adherence to the 5-Step Algorithm in rigid order:

  1. Make requirements less dumb: Question who set the requirement and why. Constraints imposed by physics or law are kept; constraints imposed by habit or tradition are challenged.
  2. Delete the part or process: Remove unused parameters, dead wrappers, and speculative branches.
  3. Simplify or optimize: Only after deleting non-essential parts, simplify the remaining core.
  4. Accelerate cycle time: Reduce test and iteration overhead.
  5. Automate: Automate the verified, simplified pipeline.

The 10% Add-Back Ledger Invariant

Musk's Rule: "If you're not adding things back 10% of the time, you're clearly not deleting enough." Every deletion and add-back is logged to .anti-slop/add-back-ledger.jsonl.

  • Target Add-Back Rate: $10% \le R \le 25%$ (Aggressive, calibrated simplification).
  • Timid ($< 10%$): Deletions are too conservative.
  • Reckless ($> 35%$): Deletions are careless and breaking active contracts.

CLI Usage

# Check current calibration status and add-back rate
bunx anti-slop-engineering reduction status --json

# Log an item removal
bunx anti-slop-engineering reduction log-remove --item "legacy_v1_router" --reason "Replaced by v2"

# Log an item reinstatement
bunx anti-slop-engineering reduction log-addback --item "legacy_v1_router" --reason "External webhook compatibility"

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.