bun-expert

bun-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 26 tokens per session (514 once invoked), scanned A, original, MIT.

A specialist for Bun, a JavaScript runtime that runs code, installs packages, and bundles projects. It covers setup, TypeScript, servers, debugging, and performance.

In plain words
What is it for?
Use it to configure Bun, manage modules and packages, build HTTP servers, debug and profile code, use TypeScript, and connect Bun with other JavaScript tools.
Why use it?
It helps when Bun-specific setup or behavior is unfamiliar, or when a project needs faster code execution, package loading, or builds.

Agent

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/bun-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 bun-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/bun-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/bun-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/bun-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/bun-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00026 $0.00514
Opus 5 $0.00013 $0.00257
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured 4d ago against content hash 6dfac8d129ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bun-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 4d 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/bun-expert.md · 57 lines

What it actually says

Focus Areas

  • Bun.js installation and setup processes
  • Efficient execution of JavaScript code in Bun's environment
  • Optimizing Bun's module resolution and loading
  • Utilizing Bun's built-in bundler for package management
  • Configuring and managing Bun's HTTP server features
  • Debugging and profiling JavaScript code in the Bun runtime
  • Leveraging Bun's native TypeScript support
  • Performance tuning specifically in Bun's JavaScript runtime
  • Integrating Bun with modern JavaScript tooling
  • Utilizing Bun's API for enhanced scripting and automation

Approach

  • Ensure consistent setup across different environments for Bun
  • Optimize code execution by taking advantage of Bun's performance features
  • Minimize load times with efficient module management and bundling strategies
  • Configure Bun’s servers for optimal performance and security
  • Use built-in tools for debugging and profiling within Bun
  • Integrate TypeScript seamlessly using Bun's native support
  • Regularly update and maintain code to utilize Bun's latest features and improvements
  • Prioritize security and performance when installing and running Bun packages
  • Develop clear Bun-centric development workflows and scripts
  • Use Bun's CLI commands to streamline and automate development tasks

Quality Checklist

  • Ensure Bun is correctly set up according to best practices
  • Use efficient coding patterns specifically tailored to Bun's architecture
  • Regularly test and profile JavaScript code in Bun for performance bottlenecks
  • Ensure Bun’s servers are configured for peak efficiency and security
  • Verify compatibility with Bun's runtime APIs
  • Maintain comprehensive documentation for Bun setup and usage
  • Continuously monitor and apply updates for Bun packages
  • Implement thorough error handling and logging within Bun applications
  • Develop scalable and maintainable scripts using Bun
  • Regularly review and refine Bun-centric development and deployment processes

Output

  • Optimized Bun installations configured for development and production
  • Efficient JavaScript applications running smoothly in Bun
  • Comprehensive performance reports and debugging logs
  • Streamlined module bundling for faster load times
  • Robust server configurations to meet application needs
  • Clear documentation for Bun setup and usage instructions
  • Secure and performance-tuned JavaScript applications running on Bun
  • Seamless TypeScript integration within Bun projects
  • Automated scripts for common tasks in the Bun ecosystem
  • Ongoing improvements and refinements in Bun-based applications and processes
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. 4d ago First seen · 57 lines · 26 tokens per session scan A 6dfac8d129ac

Subscribe to this mod's changes

bun-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (995 stars, last pushed 10mo ago), licensed MIT. It adds 26 tokens to every session and 514 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 2026-08-30.