Deuz-SDK: Instructions file for Claude Code

CLAUDE.md

Deuz-SDK CLAUDE.md is an instructions file for Claude Code from Deuz-AI/Deuz-SDK. It costs 6,143 tokens per session, scanned A, original, MIT.

Repository instructions for Deuz-AI and Deuz-SDK, an npm-workspaces monorepo containing a core AI software package and an optional React package. A monorepo keeps multiple related packages in one repository.

In plain words
What is it for?
It is for guiding work on the SDK’s core and React packages, their tests and tooling, builds, releases, and code-quality rules.
Why use it?
It gives coding agents the project structure, package boundaries, commands, and required rules they need before changing the code.

Instructions file for Claude Code

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

This is Deuz-AI/Deuz-SDK's own configuration. It tells Claude Code how to work on Deuz-SDK 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 Deuz-SDK configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Deuz-AI/Deuz-SDK. 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/Deuz-AI/Deuz-SDK/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Deuz-AI/Deuz-SDK

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 Deuz-SDK CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/deuz-ai/deuz-sdk/claude-md.svg)](https://agentmods.dev/instructions/deuz-ai/deuz-sdk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/deuz-ai/deuz-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/deuz-ai/deuz-sdk/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,143 This file is loaded in full into every session.
When invoked 6,143 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 $0.06143 $0.06143
Opus 5 $0.03071 $0.03071
Sonnet 5 $0.01229 $0.01229
Haiku 4.5 $0.00614 $0.00614

Measured 7d ago against content hash 01bd0daccf5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Deuz-SDK 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.

CLAUDE.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An npm-workspaces monorepo (root is private) with two published packages in a fixed version group:

  • packages/core@deuz-sdk/core — a pure, web-first, multi-provider AI SDK (Anthropic, OpenAI, xAI Grok, Google Gemini, Vertex, Yunwu). It depends on no other AI SDK and ships its own canonical streaming + UI protocol. Node ≥ 22, ESM+CJS dual build, zero runtime dependencies.
  • packages/react@deuz-sdk/react — thin optional React adapter (hooks + minimal headless components) binding core's chat/wire APIs to React state. No business logic lives here.

Built for the Deuz platform (Next.js + Supabase, a separate repo) and published to npm. All src/, test/, tooling/ paths in this file are relative to packages/core/ unless stated otherwise. Root-level scripts delegate into the workspaces — run commands from the repo root.

Planning docs are in Turkish: the current release's code-verified design spec lives at the repo root. For 1.9.0 there are two1.9.0-parity.md (the parity + hardening plan this release actually executes) and 1.9.0.md (the research-differentiation plan it front-runs); the parity doc says outright that it comes before the other, not instead of it. Release history is in CHANGELOG.md (changesets-generated — add entries via npm run changeset, never by hand). The README is the public-facing API tour.

Commands

All from the repo root (they fan out over the workspaces):

npm run build            # core then react: tsup → dist/ (ESM + CJS + .d.ts per subpath export)
npm run dev              # core tsup --watch
npm test                 # vitest run in every workspace
npm run test:watch       # core vitest in watch mode
npm run test:types       # vitest run --typecheck.only → test/*.test-d.ts (the surface locks)
npm run lint             # eslint per workspace (core config enforces edge-safety — see below)
npm run typecheck        # tsc --noEmit per workspace
npm run format           # prettier --write . (root-owned; packages don't carry prettier)
npm run verify:docs-refs # static lint over docs/ + skills/ + README.md (see below)
npm run verify:docs      # verify:docs-refs, then the REAL docs site build (typegen + next build)
npm run check            # the full gate: format:check + verify:docs-refs + lint + typecheck + test
                         #   + test:types + build + verify:package (publint --strict + attw)
                         #   + verify:runtime (browser bundle, no node: leaks) + verify:size (byte
                         #   budgets) + verify:api (contract ratchet)

Read the full file on GitHub · 185 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. 7d ago First seen · 185 lines · 6,143 tokens per session scan A 01bd0daccf5a

Subscribe to this mod's changes

Deuz-SDK CLAUDE.md is an instructions file published in the GitHub repository Deuz-AI/Deuz-SDK (1,291 stars, last pushed 25d ago), licensed MIT. It adds 6,143 tokens to every session, about $0.0307 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