articraft: Instructions file for Claude Code

CLAUDE.md

articraft CLAUDE.md is an instructions file for Claude Code from mattzh72/articraft. It costs 1,230 tokens per session, scanned A, original, Apache-2.0.

A project instruction guide for Articraft, a local-first system that generates and inspects articulated 3D objects from text and reference images. It explains the repository's commands, structure, and data flow.

In plain words
What is it for?
Use it when generating or drafting objects, authoring records, checking the library, running tests, formatting code, or understanding the project's tools and storage.
Why use it?
It gives coding agents the background needed to change the project safely instead of treating its custom workflows like a generic application.

Instructions file for Claude Code

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

This is mattzh72/articraft's own configuration. It tells Claude Code how to work on articraft 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 articraft configures →

About the project

Articraft is a toolset for generating, viewing, and working with articulated 3D assets from text prompts. Researchers and developers use its generation code, viewer, SDK, command-line tools, and dataset; the repository points current development to a successor project.

mattzh72/articraft · 1,494 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to mattzh72/articraft. 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/mattzh72/articraft/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mattzh72/articraft

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 articraft CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mattzh72/articraft/claude-md/github.svg)](https://agentmods.dev/instructions/mattzh72/articraft/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mattzh72/articraft/claude-md"><img src="https://agentmods.dev/badge/instructions/mattzh72/articraft/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.

agentmods 80×15 button for articraft CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mattzh72/articraft/claude-md"><img src="https://agentmods.dev/badge/instructions/mattzh72/articraft/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,230 This file is loaded in full into every session.
When invoked 1,230 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 $0.01230 $0.01230
Opus 5 $0.00615 $0.00615
Sonnet 5 $0.00246 $0.00246
Haiku 4.5 $0.00123 $0.00123

Measured 10d ago against content hash f4352a372070, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

articraft 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 10d 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 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 when working with this repository.

What This Project Is

Articraft is a local-first harness for generating and inspecting articulated 3D objects from text prompts and reference images. The code repo owns the agent runtime, SDK, CLI, storage logic, viewer API, and React/Three.js viewer. Records live in a plain local data root, usually the gitignored <repo-root>/data or an external folder passed with --data-dir or ARTICRAFT_DATA_DIR.

If the user asks Claude Code to author Articraft data, follow EXTERNAL_AGENT_DATA.md. Use uv run articraft external ...; do not manually create record folders.

Common Commands

uv sync --group dev
uv build
uv run articraft init
uv run articraft status
uv run articraft library check --require-records
uv run --group dev pytest -q

just setup
just format
just lint
just smoke-tests
just test-all

Generation and record workflows:

uv run articraft generate "prompt text"
uv run articraft generate --model gemini-3-flash-preview --image reference.png "prompt text"
uv run articraft draft "prompt text"
uv run articraft draft --image reference.png "prompt text"
uv run articraft rerun <record-id>
uv run articraft fork <record-id> "edit prompt"
uv run articraft compile <record-id>
uv run articraft view <record-id>
uv run articraft library list
uv run articraft library rebuild-manifest
uv run articraft library set-category <record-id> <category_slug>

Viewer/frontend workflows:

just viewer
just viewer-dev
uv run uvicorn viewer.api.app:app --reload --host 127.0.0.1 --port 8765
npm --prefix viewer/web run dev
npm --prefix viewer/web run build
npm --prefix viewer/web run lint
npm --prefix viewer/web run typecheck

Architecture

  • agent/ - Generation runtime, provider adapters, prompt compiler/loader, tools, cost tracking, and single-record orchestration.
  • sdk/ - Generated object SDK and agent-facing docs/examples.
  • storage/ - Local data layout, records, categories, records_manifest.jsonl, run caches, materialization metadata, and validation.
  • viewer/api/ - FastAPI surface for browsing local records and serving materialized assets.
  • viewer/web/ - React/TypeScript/Three.js viewer.
  • cli/ - Top-level articraft command.
  • tests/ - pytest tests mirroring package structure.

Read the full file on GitHub · 108 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. 10d ago First seen · 108 lines · 1,230 tokens per session scan A f4352a372070

Subscribe to this mod's changes

articraft CLAUDE.md is an instructions file published in the GitHub repository mattzh72/articraft (1,494 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,230 tokens to every session, about $0.0062 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

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

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 · 5,153 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

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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens