Bundle — Development skill for Claude Code
Track bundle size, detect heavy dependencies, compare to previous builds.
How to install Bundle
Installs to ~/.claude/skills/houseofmvps-ultraship-bundle/SKILL.md
mkdir -p ~/.claude/skills/houseofmvps-ultraship-bundle && curl -fsSL https://raw.githubusercontent.com/Houseofmvps/ultraship/HEAD/commands/bundle.md -o ~/.claude/skills/houseofmvps-ultraship-bundle/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Bundle does
description: Track bundle size, detect heavy dependencies, compare to previous builds
Run the bundle tracker on this project:
node ${CLAUDE_PLUGIN_ROOT}/tools/bundle-tracker.mjs --save
Report: total bundle size, JS/CSS/image breakdown, largest files, heavy dependencies with lighter alternatives, and comparison to previous build (if history exists). Suggest code splitting for large chunks and alternative packages for heavy dependencies.
Alternatives in Development
- Resume Work From A Handoff Document — You are tasked with resuming work from a handoff document through an interactive process 10k ★
- Gemini CLI Foundations — This repository is a comprehensive skills library for Gemini CLI - reusable, production-ready skill packages t 5.3k ★
- Claude Token Efficient — One CLAUDE.md file 3.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Bundle Analyze
Bundle size + framework detection + largest assets + heavy-dependency warnings.
Forge Stats
Track command sizes, detect bloat, compare against baselines and thresholds
Bundle Analyzer
Analyze and reduce JavaScript bundle size
List Installed
Compare optional Claude-home exports with the bundle.
Openclaw Memorybox
8+ Memory hygiene CLI for Claude Code — prevents context overflow crashes, 83% MEMORY.md size reduction, zero
Clens
Claude Code session capture and analysis. Trace tool calls, detect backtracks, analyze decisions, track edit c
Related Agents
Size Check
Build the vlist library and measure gzipped bundle sizes per feature. Use after code changes to detect size re
Claude Comparator
Blind-compares two outputs for the same task (labeled A and B) and says which is better and why. Use to compar
Cost Governor
Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost