Bun Runtime

Community

secondsky

bun-runtime

Use for Bun runtime, bunfig.toml, watch/hot modes, env vars, CLI flags, and module resolution.

Overview

Publisher	secondsky
Repository	`claude-skills`
Skill name	`bun-runtime`
Stars	219
Forks	31
Bundled files	3
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by secondsky on GitHub. Read the source before you install it.

Installation

Install the Bun Runtime AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/secondsky/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/plugins/bun/skills/bun-runtime .claude/skills/bun-runtime

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bun Runtime in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bun Runtime on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bun Runtime is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bun Runtime

Bun is a fast all-in-one JavaScript runtime built on JavaScriptCore (Safari's engine). It provides 4x faster startup than Node.js on Linux.

Quick Start

bash
# Run a file
bun run index.ts
bun index.ts  # shorthand

# Run with watch mode
bun --watch run index.ts

# Run package.json script
bun run dev

# Run with hot reloading
bun --hot run server.ts

Core CLI Flags

Flag	Purpose
`--watch`	Restart on file changes
`--hot`	Hot module replacement (preserves state)
`--smol`	Reduce memory usage (slower GC)
`--inspect`	Enable debugger
`--preload`	Load modules before execution
`--env-file`	Load specific .env file
`-e, --eval`	Evaluate code string

Running Files

Bun transpiles TypeScript and JSX on-the-fly:

bash
bun run index.js
bun run index.ts
bun run index.jsx
bun run index.tsx

Important: Put Bun flags immediately after bun:

bash
bun --watch run dev    # Correct
bun run dev --watch    # Wrong - flag passed to script

Package.json Scripts

bash
# Run script
bun run dev
bun dev  # shorthand (if no Bun command conflicts)

# List available scripts
bun run

# Run with Bun instead of Node
bun run --bun vite

Bun respects lifecycle hooks (preclean, postclean, etc.).

Watch Mode vs Hot Reloading

Mode	Flag	Behavior
Watch	`--watch`	Full process restart on changes
Hot	`--hot`	Replace modules, preserve state

bash
# Watch mode - full restart
bun --watch run server.ts

# Hot reloading - preserves connections/state
bun --hot run server.ts

Environment Variables

Bun automatically loads .env files:

bash
# Loads automatically: .env, .env.local, .env.development
bun run index.ts

# Specify env file
bun --env-file .env.production run index.ts

# Disable auto-loading
# In bunfig.toml: env = false

Access in code:

typescript
const apiKey = process.env.API_KEY;
const bunEnv = Bun.env.NODE_ENV;

Globals Available

Global	Source	Notes
`Bun`	Bun	Main API object
`Buffer`	Node.js	Binary data
`process`	Node.js	Process info
`fetch`	Web	HTTP requests
`Request/Response`	Web	HTTP types
`WebSocket`	Web	WebSocket client
`crypto`	Web	Cryptography
`console`	Web	Logging
`__dirname`	Node.js	Current directory
`__filename`	Node.js	Current file

Preload Scripts

Load modules before your main script:

bash
bun --preload ./setup.ts run index.ts

Or in bunfig.toml:

toml
preload = ["./setup.ts"]

Use cases: polyfills, global setup, instrumentation.

Stdin Execution

bash
# Pipe code to Bun
echo "console.log('Hello')" | bun run -

# Redirect file
bun run - < script.js

Workspaces & Monorepos

bash
# Run script in specific packages
bun run --filter 'pkg-*' build

# Run in all workspaces
bun run --filter '*' test

Debugging

bash
# Start debugger
bun --inspect run index.ts

# Wait for debugger connection
bun --inspect-wait run index.ts

# Break on first line
bun --inspect-brk run index.ts

Connect via Chrome DevTools or VS Code.

Common Errors

Error	Cause	Fix
`Cannot find module`	Missing dependency	Run `bun install`
`Top-level await`	Using await outside async	Wrap in async function or use `.mts`
`--watch not working`	Flag in wrong position	Put flag before `run`

When to Load References

Load references/bunfig.md when:

Configuring bunfig.toml
Setting up test configuration
Configuring package manager behavior
Setting JSX options

Load references/cli-flags.md when:

Need complete CLI flag reference
Configuring advanced runtime options
Setting up debugging

Load references/module-resolution.md when:

Troubleshooting import errors
Configuring path aliases
Understanding Bun's resolution algorithm

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bun Runtime AI skill do?

Use for Bun runtime, bunfig.toml, watch/hot modes, env vars, CLI flags, and module resolution.

Why use Bun Runtime on TypingMind?

Because you install it once and use it with any model. Bun Runtime is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bun Runtime in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/secondsky/claude-skills/tree/main/plugins/bun/skills/bun-runtime. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bun Runtime?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bun Runtime?

As many as you like. As long as a model supports skills, you can use Bun Runtime with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bun Runtime AI skill free?

Yes. It is published on GitHub by secondsky under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Claude Handoff

mattpocock

CommunityPopular

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Finishing A Development Branch

obra

CommunityPopular

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Receiving Code Review

obra

CommunityPopular

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative…

Requesting Code Review

obra

CommunityPopular

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Bun Runtime

Quick Start

Core CLI Flags

Running Files

Package.json Scripts

Watch Mode vs Hot Reloading

Environment Variables

Globals Available

Preload Scripts

Stdin Execution

Workspaces & Monorepos

Debugging

Common Errors

When to Load References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now