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.
curl -O https://raw.githubusercontent.com/petarzarkov/dunx/main/CLAUDE.mdgit clone --depth 1 https://github.com/petarzarkov/dunxWrote 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/instructions/petarzarkov/dunx/claude-md)<a href="https://agentmods.dev/instructions/petarzarkov/dunx/claude-md"><img src="https://agentmods.dev/badge/instructions/petarzarkov/dunx/claude-md/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/instructions/petarzarkov/dunx/claude-md"><img src="https://agentmods.dev/badge/instructions/petarzarkov/dunx/claude-md.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 | $0.02725 | $0.02725 |
| Opus 5.5 | $0.01090 | $0.01090 |
| Sonnet 5.5 | $0.00545 | $0.00545 |
| Haiku 4.5 | $0.00272 | $0.00272 |
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 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 — 226 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, published as ten workspaces
under @dunx/*.
Most rules in this repo are enforced by a gate, not by this file. Write the
change, then run bun run ci (35s, every gate CI runs). It names what it wants.
Do not try to satisfy the checks from memory before you have run them once.
The reasoning behind every rule here, including what was measured and what was tried and reversed, is in internal/notes/research/repo-rules-rationale.md. Read it when you need to know why, not to find out what.
The four rules
Rule 1 - native implementations only. Every capability is built on a Bun.*
API, a Web standard Bun implements, or a native module via N-API. Never
reimplement what Bun already does (Bun.serve, Bun.SQL, bun:sqlite,
Bun.RedisClient, Bun.Glob, Bun.password, Bun.S3Client). Never invent what
a mature library already solves: dunx integrates zod, drizzle-orm, better-auth
and bullmq rather than competing with them, and they are peers, never
dependencies. A dependency of a published workspace may only be @arkv/*,
@dunx/* or oxc-parser.
→ scripts/rule-native.test.ts
Rule 2 - one declaration, at the lowest common owner. Before writing
anything, search for it. If a second copy would exist, move the first somewhere
both can reach and delete it in the same change. This covers code, types,
constants and styles. Two frontends needing a component means @dunx/ui; two
packages needing a traversal means it moves down to the package that owns the
data; a wire format is declared by the server and imported by the frontend with a
relative import type.
Not gated. It is the rule most often broken while adding a feature.
Rule 3 - a package's surface is classes. In packages/* and tools/*,
anything with state, configuration or a lifetime is a class, and anything a
consumer injects must be a class (the container resolves runtime values; an
interface at an injection site is a boot error). A module is a class with static
forRoot/forRootAsync. The exception is a pure, stateless, argument-in
value-out function nobody configures. internal/* is exempt.
Not gated.
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 Changed · +10 tokens per session 0a15fffe7dbc
- 15d ago Changed a72780f13908
- 1mo ago Changed · +2 lines · +46 tokens per session b99cb6bc57a3
- 1mo ago Changed · -822 lines · -12,871 tokens per session scan C → A b93449c81d3e
- 1mo ago Changed · +25 lines · +467 tokens per session scan A → C a1417abc57ab
- 1mo ago Changed · +3 tokens per session 67639b117f65
- 1mo ago Changed · +10 lines · +178 tokens per session 6cfb22c50e20
- 1mo ago Changed · +1 lines · +25 tokens per session 95b4858ab661
- 1mo ago Changed · +48 lines · +764 tokens per session 0294735c5570
- 2mo ago First seen · 962 lines · 14,103 tokens per session scan A aa769f38a190
dunx CLAUDE.md is an instructions file published in the GitHub repository petarzarkov/dunx (93 stars, last pushed today), licensed MIT. It adds 2,725 tokens to every session, about $0.0109 per session on Opus 5.5. 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 instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.