Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/secondsky/claude-skillsnpx agentmods add skills/secondsky/claude-skills/bun-bundlerWrote 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/skills/secondsky/claude-skills/bun-bundler)<a href="https://agentmods.dev/skills/secondsky/claude-skills/bun-bundler"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/bun-bundler/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/secondsky/claude-skills/bun-bundler"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/bun-bundler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 5.1 | $0.00090 | $0.02022 |
| Opus 5 | $0.00045 | $0.01011 |
| Sonnet 5 | $0.00018 | $0.00404 |
| Haiku 4.5 | $0.00009 | $0.00202 |
Grade A, and why
bun-bundler 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bun Bundler
Bun's bundler is a fast JavaScript/TypeScript bundler built on the same engine as Bun's runtime. It's an esbuild-compatible alternative with native performance.
Quick Start
CLI
# Basic bundle
bun build ./src/index.ts --outdir ./dist
# Production build
bun build ./src/index.ts --outdir ./dist --minify
# Multiple entry points
bun build ./src/index.ts ./src/worker.ts --outdir ./dist
JavaScript API
// Since Bun 1.2, Bun.build REJECTS on failure (throws).
// Wrap in try/catch to handle errors; pass { throw: false } to restore the
// old resolve-with-{ success, logs } contract if you prefer that style.
try {
const result = await Bun.build({
entrypoints: ["./src/index.ts"],
outdir: "./dist",
});
console.log(`Built ${result.outputs.length} files`);
} catch (err) {
console.error("Build failed:", err);
process.exit(1);
}
Bun.build Options
await Bun.build({
// Entry points (required)
entrypoints: ["./src/index.ts"],
// Output directory
outdir: "./dist",
// Target environment
target: "browser", // "browser" | "bun" | "node"
// Output format
format: "esm", // "esm" | "cjs" | "iife"
// Minification
minify: true, // or { whitespace: true, identifiers: true, syntax: true }
// Code splitting
splitting: true,
// Source maps
sourcemap: "external", // "none" | "inline" | "external" | "linked"
// Naming patterns
naming: {
entry: "[dir]/[name].[ext]",
chunk: "[name]-[hash].[ext]",
asset: "[name]-[hash].[ext]",
},
// Define globals
define: {
"process.env.NODE_ENV": JSON.stringify("production"),
},
// External packages
external: ["react", "react-dom"],
// Loaders
loader: {
".svg": "text",
".png": "file",
},
// Plugins
plugins: [myPlugin],
// Root directory
root: "./src",
// Public path for assets
publicPath: "/static/",
});
CLI Flags
bun build <entrypoints> [flags]
| Flag | Description |
|---|---|
--outdir |
Output directory |
--outfile |
Output single file |
--target |
browser, bun, node |
--format |
esm, cjs, iife |
--minify |
Enable minification |
--minify-whitespace |
Minify whitespace only |
--minify-identifiers |
Minify identifiers only |
--minify-syntax |
Minify syntax only |
--splitting |
Enable code splitting |
--sourcemap |
none, inline, external, linked |
--external |
Mark packages as external |
--define |
Define compile-time constants |
--loader |
Custom loaders for extensions |
--public-path |
Public path for assets |
--root |
Root directory |
--entry-naming |
Entry point naming pattern |
--chunk-naming |
Chunk naming pattern |
--asset-naming |
Asset naming pattern |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 330 lines · 90 tokens per session scan A f4ee876e535d
bun-bundler is a skill published in the GitHub repository secondsky/claude-skills (217 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 2,022 once invoked, about $0.0005 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.
Other skills, from other repositories
avoid-for
Avoid for loops (C-style, for...of, for...in) in TypeScript/JavaScript. Prefer higher-order Array methods like map, filter, find, some, every, reduce. Use when writing or reviewing loops or iteration over arrays, objects, Map, Set, or String.
async-state-type
Avoid contradictory state types for async data fetching. Use Suspense or discriminated unions instead. Use when writing or reviewing async data fetching code in React/TypeScript.
file-naming
File and directory naming conventions for TypeScript/JavaScript projects. Use when creating new files or directories.
senior-frontend
Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
nextjs-typescript-engineer
This skill should be used when the user asks to "set up a Next.js TypeScript project", "define code conventions", "organize project structure", "implement component patterns", "enforce type safety", or mentions "next.js project", "typescript convention", "code style", "project structure", "component pattern", "api…
frontend-ai-guide
Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.