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.
npx agentmods add agents/0xfurai/claude-code-subagents/bun-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWrote 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.
[](https://agentmods.dev/agents/0xfurai/claude-code-subagents/bun-expert)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 4d ago First seen · 57 lines · 26 tokens per session scan A 6dfac8d129ac
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.