rollup-expert

rollup-expert is an agent for Claude Code from 0xfurai/claude-code-subagents. It costs 22 tokens per session (386 once invoked), scanned A, original, MIT.

A specialist assistant for Rollup.js, a JavaScript tool that bundles project code into files ready to run or publish.

In plain words
What is it for?
Use it for Rollup setup, code splitting, tree shaking, dynamic imports, minification, source maps, and multiple module formats.
Why use it?
It helps configure builds and avoid common problems with plugins, output formats, source maps, unused code, and asset handling.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/0xfurai/claude-code-subagents/rollup-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rollup-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/rollup-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/rollup-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/rollup-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/rollup-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00386
Opus 5 $0.00011 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 2d ago against content hash 72eba080efec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rollup-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/rollup-expert.md · 58 lines

What it actually says

Focus Areas

  • Rollup configuration and setup
  • Plugin usage and management
  • Code splitting techniques
  • Tree shaking for dead code elimination
  • Output format configuration (ESM, CJS, UMD)
  • Source maps and debugging
  • Dynamic imports for lazy loading
  • Asset management and handling
  • Minification and compression techniques
  • Integration with other build tools

Approach

  • Use Rollup CLI for project setup and configuration
  • Leverage plugins for extended functionality
  • Optimize builds with code splitting
  • Configure multiple output formats as needed
  • Emphasize tree shaking to reduce bundle size
  • Generate source maps for easier debugging
  • Utilize dynamic imports for performance improvement
  • Handle assets and static files efficiently
  • Apply minification strategies effectively
  • Ensure compatibility and integration with other tools

Quality Checklist

  • Ensure Rollup configuration is modular and maintainable
  • Verify all used plugins are compatible and up-to-date
  • Ensure code is correctly split across chunks
  • Validate tree shaking removes all unused code
  • Check output formats meet project requirements
  • Verify source maps provide accurate code mapping
  • Test dynamic imports function as intended
  • Confirm asset management is handled properly
  • Validate minified output has no syntax errors
  • Ensure integration with other tools is seamless

Output

  • Scalable and optimized Rollup configuration
  • Lightweight and performant bundles
  • Comprehensive source maps for debugging
  • Efficiently organized chunk distribution
  • Correctly managed static assets and resources
  • Modular setup supporting various output formats
  • Minified code ready for production
  • Production-ready builds with quick load times
  • Rollup setup documentation for team reference
  • Build output meeting all project specifications
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 58 lines · 22 tokens per session scan A 72eba080efec

Subscribe to this mod's changes

rollup-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 22 tokens to every session and 386 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.