agent-booster

SkillProductivity

Lets your agent edit code files instantly using fast built-in transformations instead of slow AI generation.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the agent-booster skill

About this capability

WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/ruflo/skills/agent-booster/SKILL.md and read by ahel’s review.

  • High-frequency repetitive modifications
  • When latency is critical (<1ms requirement)
  • Cost-sensitive batch operations

Supported Transforms

TransformDescriptionExample
var-to-constModernize variable declarationsvar x = 1 -> const x = 1
add-typesInsert TypeScript annotationsfunction f(x) -> function f(x: string)
add-error-handlingWrap in try/catchBare calls -> try/catch blocks
async-awaitConvert Promise chains.then().catch() -> async/await
extract-functionExtract code blocksInline code -> named function
inline-variableInline single-use variablesRemove intermediate vars
add-jsdocGenerate documentationBare functions -> JSDoc comments

Performance

  • Execution: <1ms per transform
  • Cost: $0 (no LLM invocation)
  • Speedup: 352x compared to LLM inference
  • Confidence threshold: >90% pattern match required

Agents Used

  • agents/coder/ - Fallback for unmatched patterns

Tool Use

Invoke via babysitter process: methodologies/ruflo/ruflo-task-routing

Signals

GitHub stars
2k
Forks
106
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
agent-booster
Source
github.com/a5c-ai/babysitter