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.
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.
curl -O https://raw.githubusercontent.com/mattzh72/articraft/main/AGENTS.mdgit clone --depth 1 https://github.com/mattzh72/articraftWrote 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/mattzh72/articraft/agents-md)<a href="https://agentmods.dev/instructions/mattzh72/articraft/agents-md"><img src="https://agentmods.dev/badge/instructions/mattzh72/articraft/agents-md.svg" alt="Measured on agentmods" 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 | $0.01553 | $0.01553 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
articraft AGENTS.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 8d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
agent/ contains the generation runtime, provider adapters, prompt compiler/loader, tools, cost tracking, TUI helpers, and single-record orchestration. storage/ owns the gitignored local data/ layout, records, categories, records_manifest.jsonl, run caches, and materialization metadata. sdk/ and sdk/_core/ define the articulated-object SDK layers; sdk/_docs/ and sdk/_examples/ are agent-facing authoring assets. viewer/api/ exposes the FastAPI surface, and viewer/web/ is the React/TypeScript/Three.js viewer. cli/ contains the articraft entry points. tests/ mirrors the main packages with focused smoke/regression coverage.
Build, Test, and Development Commands
Use uv run articraft ... for product workflows, and just for local setup/check/viewer shortcuts. Run just to list available shortcuts.
uv sync --group devinstalls Python and development dependencies.just setupbootstraps.env, syncs dependencies, installs viewer dependencies whennpmexists, and initializes storage.uv buildcreates the wheel and source distribution indist/.uv run articraft initcreates the gitignored localdata/tree and empty library manifest.uv run articraft statusshows local library status.uv run --group dev pytest -qruns the full Python regression suite.just smoke-testsruns the fast pre-push suite;just test-allruns the full Python suite.just formatrunsruff format .;just lintrunsruff check ..uv run articraft library checkvalidates local library format.uv run articraft env bootstrapcreates.envfrom.env.examplewithout overwriting existing secrets.
Generation, Dataset, and Viewer Commands
- External agent data generation must follow
EXTERNAL_AGENT_DATA.md. If the user asks Codex, Claude Code, Cursor, or another external harness to generate Articraft data, useuv run articraft external ...; do not manually create records or use an alternate workflow. uv run articraft generate "prompt text"writes a local library record.uv run articraft generate --model gemini-3-flash-preview --image reference.png "prompt text"overrides model and adds a reference image.uv run articraft draft "prompt text"creates a draft local record without running generation.uv run articraft draft --image reference.png "prompt text"stores a reference image with the draft.uv run articraft rerun <record-id>reruns generation for an existing record.uv run articraft compile <record-id>recompiles one record into<data-root>/cache/record_materialization/<id>/.uv run articraft library listlists records fromrecords_manifest.jsonl.uv run articraft library rebuild-manifestrebuildsrecords_manifest.jsonlfromrecords/.uv run articraft library check --require-recordsvalidates that manifest rows point at real records.just viewerstarts the built viewer flow;just viewer-devstarts uvicorn and Vite together.uv run uvicorn viewer.api.app:app --reload --host 127.0.0.1 --port 8765starts only the API.npm --prefix viewer/web run dev,build,lint, andtypecheckrun frontend-only workflows.
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.
- 8d ago First seen · 54 lines · 1,553 tokens per session scan A 2dd24d1457a6
articraft AGENTS.md is an instructions file published in the GitHub repository mattzh72/articraft (1,492 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,553 tokens to every session, about $0.0078 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.
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.
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.
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 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).
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.