What is viznoir CLAUDE.md?

Project instructions for Viznoir, a Python MCP server for creating high-quality scientific visualizations with VTK, a library for 3D graphics and visual data analysis.

Use them when developing Viznoir, running its tests or checks, installing optional mesh or image features, or starting its MCP server.

They provide the commands and project details needed to install, test, lint, type-check, and run the server reliably.

How kimimgo/viznoir configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kimimgo/viznoir. 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/kimimgo/viznoir/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kimimgo/viznoir

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kimimgo/viznoir/claude-md.svg)](https://agentmods.dev/instructions/kimimgo/viznoir/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kimimgo/viznoir/claude-md"><img src="https://agentmods.dev/badge/instructions/kimimgo/viznoir/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,647 This file is loaded in full into every session.

When invoked 2,647 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.

Model	Per session	Once invoked
Fable 5.1	$0.02647	$0.02647
Opus 5	$0.01324	$0.01324
Sonnet 5	$0.00529	$0.00529
Haiku 4.5	$0.00265	$0.00265

Measured 8d ago against content hash c48d6102feea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

viznoir 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 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.

CLAUDE.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 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.

viznoir

VTK is all you need. Cinema-quality science visualization for AI agents.

Project Info

Repo: kimimgo/viznoir
Language: Python 3.10+
MCP SDK: fastmcp>=2.0.0
PyPI: viznoir
Entry point: mcp-server-viznoir → viznoir.server:main

Development Commands

# Install (editable with dev deps)
pip install -e ".[dev]"

# Run all tests (1650+ tests, async mode=auto)
pytest --cov=viznoir --cov-report=term-missing -q

# Run a single test file
pytest tests/test_engine/test_filters.py -q

# Run a single test function
pytest tests/test_engine/test_filters.py::test_slice_plane -q

# Lint
ruff check src/ tests/

# Lint + auto-fix
ruff check src/ tests/ --fix

# Type check
mypy src/viznoir/ --ignore-missing-imports

# Install with optional deps (meshio/trimesh or pillow/matplotlib)
pip install -e ".[mesh]"       # mesh format conversion
pip install -e ".[composite]"  # split_animate (Pillow + matplotlib)
pip install -e ".[all]"        # everything

# Run MCP server locally (stdio mode)
mcp-server-viznoir

# Landing page (www/)
cd www && npm install && npm run dev    # dev server
cd www && npm run build                 # production build

# Docker (GPU EGL headless)
docker compose build
docker compose up                       # stdio mode, GPU required

CI runs on Python 3.10, 3.11, 3.12, 3.13: lint → type check → test. Coverage threshold ≥80% enforced on 3.12.

Architecture

Layer 3: Skills (자연어 인터페이스)        ← .claude-plugin/skills/
  cae-postprocess (도메인 전문가 통역 — CFD/FEA/SPH)

Layer 2: Agents (전문 서브에이전트)        ← agents/
  viz-agent (sonnet), mesh-agent (haiku)

Layer 1: MCP Server (viznoir)  ← src/viznoir/
  VTK direct API → 헤드리스 렌더링 (ParaView 불필요)
  meshio → 50+ 형식 변환, trimesh → STL/OBJ/PLY 분석

Data Flow (Tool Call → PNG)

server.py (MCP tool)
  → tools/*.py (impl: build PipelineDefinition)
    → core/compiler.py (ScriptCompiler: PipelineDefinition → Python script string)
      → core/runner.py (VTKRunner: in-process executor or Docker)
        → engine/*.py (VTK direct API: readers, filters, renderer, camera)
          → core/output.py (OutputHandler: RunResult → PipelineResult)

Read the full file on GitHub · 207 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.

8d ago First seen · 207 lines · 2,647 tokens per session scan A c48d6102feea

Subscribe to this mod's changes

viznoir CLAUDE.md is an instructions file published in the GitHub repository kimimgo/viznoir (17 stars, last pushed yesterday), licensed MIT. It adds 2,647 tokens to every session, about $0.0132 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.

Scientific ai-agents cfd headless-rendering mcp model-context-protocol openfoam

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

viznoir: Instructions file for Claude Code