SkillOptimizer

Work Execution Command

Runfusion/FusionSource at 779cd2e (opens GitHub)

49% lighter

Same results: 29 of 30 checks passed, original 25 of 30

539,226 tokens, was 1,065,055 across 2 tasks, 3 runs each

Check it yourself

SKILL.md unchanged, word for word

What AIR found

  • VerifiedNo high-risk findings

    AIR's security review found nothing that needs a closer look. Reviewed Oct 1, 2026.

What changed

Original on GitHub
Files in the skill and how each changed
SKILL.mdNot in the original · Not in the lighter versionUnchanged
hooks/gate.mjsNot in the original · 97 linesAdded
.claude/settings.jsonNot in the original · 1 entryModified

The rules hooks/gate.mjs holds

It runs before every Bash command and refuses the ones the skill's own rules forbid, quoting the rule back to the agent. Reads always pass.

Task by task

  • Unified plan multi unit57% lighter

    Original
    811,427 tokens
    Lighter version
    346,105 tokens
  • Bare prompt validation feature24% lighter

    Original
    253,628 tokens
    Lighter version
    193,121 tokens
Tokens per task, the middle of 3 runs each, on one scale.

Measured in the rule-check study, Sep 18, 3 runs per task, graded blind. How we measured

Embed badge
SkillOptimizer result
Markdown
[![SkillOptimizer result](/badge/ce-work.svg)](/skills/ce-work)

HTML
<a href="/skills/ce-work"><img src="/badge/ce-work.svg" alt="SkillOptimizer result" /></a>