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/MadAppGang/claude-codenpx agentmods add skills/madappgang/claude-code/bunjsWrote 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/madappgang/claude-code/bunjs)<a href="https://agentmods.dev/skills/madappgang/claude-code/bunjs"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/bunjs/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/madappgang/claude-code/bunjs"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/bunjs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.05790 |
| Opus 5.5 | $0.00020 | $0.02316 |
| Sonnet 5.5 | $0.00010 | $0.01158 |
| Haiku 4.5 | $0.00005 | $0.00579 |
Grade A, and why
bunjs scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fetch(req, server) { How it starts
The opening of the file, as written. The whole thing — 853 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bun.js Backend Patterns
Overview
Bun runtime patterns for building fast TypeScript backend services. This skill covers core Bun features, HTTP servers with Hono, database access with Prisma, validation with Zod, error handling, testing, and configuration patterns.
When to use this skill:
- Implementing basic HTTP endpoints and route handlers
- Setting up middleware patterns (CORS, logging, auth)
- Working with SQLite or PostgreSQL databases
- Implementing request validation with Zod
- Writing tests with Bun's native test runner
- Basic file operations and WebSocket handling
For advanced topics, see:
- dev:bunjs-architecture - Layered architecture, clean code patterns, camelCase conventions
- dev:bunjs-production - Docker, AWS, Redis caching, security, CI/CD
- dev:bunjs-apidog - OpenAPI specs and Apidog integration
Why Bun
Bun fundamentally transforms TypeScript backend development by:
- Native TypeScript execution - No build steps in development
- Lightning-fast performance - 3-4x faster than Node.js for many operations
- Unified toolkit - Built-in test runner, bundler, and transpiler
- Drop-in compatibility - Most Node.js APIs and npm packages work
- Developer experience - Hot reload with
--hot, instant feedback
Stack Overview
- Bun 1.x (runtime, package manager, test runner, bundler)
- TypeScript 5.7 (strict mode)
- Hono 4.6 (ultra-fast web framework, TypeScript-first)
- Prisma 6.2 (type-safe ORM)
- Biome 2.3 (formatting + linting, replaces ESLint + Prettier)
- Zod (runtime validation)
- PostgreSQL 17 / SQLite (database)
Project Structure
project-root/
├── src/
│ ├── server.ts # Entry point (starts server)
│ ├── app.ts # Hono app initialization & middleware
│ ├── config.ts # Environment configuration
│ ├── core/ # Core utilities (errors, logger, responses)
│ ├── database/
│ │ ├── client.ts # Prisma client setup
│ │ └── repositories/ # Data access layer (Prisma queries)
│ ├── services/ # Business logic layer
│ ├── controllers/ # HTTP handlers (calls services)
│ ├── middleware/ # Hono middleware (auth, validation, etc.)
│ ├── routes/ # API route definitions
│ ├── schemas/ # Zod validation schemas
│ ├── types/ # TypeScript type definitions
│ └── utils/ # Utility functions
├── tests/
│ ├── unit/ # Unit tests
│ └── integration/ # Integration tests (API + DB)
├── prisma/ # Prisma schema & migrations
├── tsconfig.json # TypeScript config
├── biome.json # Biome config
├── package.json # Bun-managed dependencies
└── bun.lockb # Bun lockfile
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.
- 1mo ago First seen · 853 lines · 49 tokens per session scan A af1d1216e652
bunjs is a skill published in the GitHub repository MadAppGang/claude-code (286 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 5,790 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bun-docs
Bun 1.2 — runtime, package manager, HTTP server, SQLite, test runner, bundler, TypeScript, FFI, shell API.
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
Drizzle ORM Testing
Testing patterns for Drizzle ORM covering migration testing, query builder testing, transaction testing, and database integration testing with PostgreSQL, SQLite, and MySQL.
Bun Test Runner
Fast test execution with Bun's built-in test runner including snapshot testing, mocking, code coverage, lifecycle hooks, DOM testing with happy-dom, and migration from Jest and Vitest to Bun test.
component-tester
Run Vitest tests for a specific component with coverage. Use when making changes to React components to ensure tests pass and coverage is maintained.
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.