agent-booster
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
Best use case
agent-booster is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
Teams using agent-booster should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-booster/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-booster Compares
| Feature / Agent | agent-booster | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Agent Booster ## Overview WASM-compiled code transformation engine for simple, well-defined tasks. Bypasses LLM inference entirely for pattern-matched transforms, achieving sub-millisecond execution at zero cost. ## When to Use - Simple, deterministic code transforms - 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`
Related Skills
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.
issue
Run an issue-centric Babysitter workflow.