# Agent Booster

> Agent Booster is an Agent Skill for development published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

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

- Skill name: `agent-booster`
- Category: [Development](https://www.openparable.com/skill/development/1)
- Source: https://github.com/a5c-ai/babysitter/blob/HEAD/library/methodologies/ruflo/skills/agent-booster/SKILL.md
- Repository: a5c-ai/babysitter (1,548 GitHub stars when collected)

## SKILL.md

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

## Supported Transforms

| Transform | Description | Example |
|-----------|-------------|---------|
| `var-to-const` | Modernize variable declarations | `var x = 1` -> `const x = 1` |
| `add-types` | Insert TypeScript annotations | `function f(x)` -> `function f(x: string)` |
| `add-error-handling` | Wrap in try/catch | Bare calls -> try/catch blocks |
| `async-await` | Convert Promise chains | `.then().catch()` -> `async/await` |
| `extract-function` | Extract code blocks | Inline code -> named function |
| `inline-variable` | Inline single-use variables | Remove intermediate vars |
| `add-jsdoc` | Generate documentation | Bare 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`

---

Source: https://www.openparable.com/skill/development/agent-booster (OpenParable). Cite the canonical URL above.
