dunx: Instructions file for Claude Code

CLAUDE.md

dunx CLAUDE.md is an instructions file for Claude Code from petarzarkov/dunx. It costs 14,892 tokens per session, scanned A, original, MIT.

Repository instructions for dunx, a Bun-native dependency-injection framework; dependency injection is a way to provide code with the services it needs instead of creating them itself.

In plain words
What is it for?
Use them when developing dunx or its packages, choosing implementations, or deciding whether an existing Bun API or workspace library should be extended.
Why use it?
They set boundaries for design decisions, require using Bun's built-in features where available, and point agents to the project's architecture, roadmap, and reference implementations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is petarzarkov/dunx's own configuration. It tells Claude Code how to work on dunx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dunx configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is tsconfig.json # Extends ../../tsconfig.json - one per package, no build variants.

Reuse

Borrowing it

Nothing to install: this file belongs to petarzarkov/dunx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/petarzarkov/dunx/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/petarzarkov/dunx

Made for: Claude Code.

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 dunx CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/petarzarkov/dunx/claude-md.svg)](https://agentmods.dev/instructions/petarzarkov/dunx/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/petarzarkov/dunx/claude-md"><img src="https://agentmods.dev/badge/instructions/petarzarkov/dunx/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 14,892 This file is loaded in full into every session.
When invoked 14,892 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.14892 $0.14892
Opus 5 $0.07446 $0.07446
Sonnet 5 $0.02978 $0.02978
Haiku 4.5 $0.01489 $0.01489

Measured yesterday against content hash 95b4858ab661, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dunx CLAUDE.md 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 yesterday.

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.

CLAUDE.md · 1,011 lines

How it starts

The opening of the file, as written. The whole thing — 1,011 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dunx - Claude Code Instructions

dunx is a Bun-native dependency injection framework. Read docs/ARCHITECTURE.md before making design decisions - it records what was measured, what was rejected, and why. Read docs/ROADMAP.md for what is next, what is still open, and the reference implementations in nestjs-template to work from instead of designing from scratch.

Rule 1 - native implementations only

This rule outranks every other consideration in this file. If satisfying it and satisfying something else below are in conflict, this one wins, and the conflict is worth raising rather than resolving quietly.

Every capability dunx ships must be built on a Bun-native API or, failing that, a native low-level implementation - compiled, not JavaScript reimplementations of things the platform already does. oxc-parser in @dunx/transform is the reference precedent: a Rust parser via N-API, chosen over a JavaScript AST library.

There are two halves to this, and they pull in opposite directions on purpose.

Never reimplement what Bun already does

If Bun ships it, use Bun. A JavaScript reimplementation of a platform primitive is slower, larger, and a maintenance liability. In order of preference:

  1. A Bun.* API or bun:* module - Bun.serve, Bun.SQL, bun:sqlite, Bun.RedisClient, Bun.file, Bun.Image, Bun.Glob, Bun.password, Bun.CryptoHasher, Bun.color, Bun.enableANSIColors, Bun.S3Client. See docs/bun-apis.md.
  2. A Web standard Bun implements natively - Request, Response, Blob, URL, WebSocket, ReadableStream, crypto.subtle, AsyncLocalStorage.
  3. A native module via N-API, like oxc-parser. Needs a note in ARCHITECTURE.md saying which Bun API was missing.

Banned because Bun already does the job: express, ws, socket.io, ioredis, pg, mysql2, better-sqlite3, postgres.js, sharp, jimp, image-size, glob, chokidar, axios, node-fetch, bcrypt, dotenv, @aws-sdk/*, lodash.

Read the full file on GitHub · 1,011 lines

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. yesterday Changed · +1 lines · +25 tokens per session 95b4858ab661
  2. 3d ago Changed · +48 lines · +764 tokens per session 0294735c5570
  3. 7d ago First seen · 962 lines · 14,103 tokens per session scan A aa769f38a190

Subscribe to this mod's changes

dunx CLAUDE.md is an instructions file published in the GitHub repository petarzarkov/dunx (21 stars, last pushed yesterday), licensed MIT. It adds 14,892 tokens to every session, about $0.0745 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens