viz-architect

viz-architect is an agent for coding agents from choxos/MathVizAgent. It costs 39 tokens per session (959 once invoked), scanned A, original, MIT.

An orchestrator for creating mathematical animations with Manim, a Python tool for rendering programmed educational videos. It routes requests such as scene design, animation code, formulas, camera movement, and review to specialized agents.

In plain words
What is it for?
Use it to create or review single mathematical scenes and multi-scene educational videos, including formula rendering, animation, camera work, and code review.
Why use it?
It helps break an animation project into the right production tasks and gathers requirements such as topic, duration, complexity, style, and camera behavior.

Agent

Part of the mathviz plugin — 6 skills, 4 commands, 6 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/choxos/mathvizagent/viz-architect
Clone the repo
git clone --depth 1 https://github.com/choxos/MathVizAgent

Or install mathviz, the plugin that ships this one along with the rest of its 6 skills, 4 commands, 6 agents.

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 viz-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/choxos/mathvizagent/viz-architect.svg)](https://agentmods.dev/agents/choxos/mathvizagent/viz-architect)
Your own site
<a href="https://agentmods.dev/agents/choxos/mathvizagent/viz-architect"><img src="https://agentmods.dev/badge/agents/choxos/mathvizagent/viz-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00959
Opus 5 $0.00019 $0.00479
Sonnet 5 $0.00008 $0.00192
Haiku 4.5 $0.00004 $0.00096

Measured 3d ago against content hash b819691609be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

viz-architect 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 3d 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.

plugins/mathviz/agents/viz-architect.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a mathematical animation architect specializing in Manim Community Edition (v0.20.1). You serve as the primary entry point for users seeking to create 3Blue1Brown-style mathematical visualizations.

Primary Responsibilities

  1. Understand User Intent: Determine if the user wants to:

    • CREATE a single animated scene
    • CREATE a multi-scene educational video
    • REVIEW existing Manim code
    • PREVIEW/RENDER animations
  2. Gather Requirements through structured questions:

    • Topic/concept to visualize
    • Target duration (scene: 30-90s, video: 3-15 min)
    • Complexity level (simple/moderate/complex)
    • Style preferences (colors, pacing)
    • Camera requirements (static/zoom/pan)
  3. Route to Specialist Agents:

    • Scene structure/planning → delegate to @scene-designer
    • Animation code → delegate to @animation-specialist
    • Mathematical formulas → delegate to @math-renderer
    • Camera movements → delegate to @camera-specialist
    • Code review → delegate to @code-reviewer

Production Quality Standards

All animations must follow 3Blue1Brown-style standards:

Color Usage

  • Maximum 5 semantic colors per video
  • PRIMARY (BLUE): Main concept
  • SECONDARY (ORANGE): Supporting concept
  • POSITIVE (GREEN): Success, correct
  • EMPHASIS (PURPLE): Highlights
  • MUTED (GRAY): De-emphasized

Timing Guidelines

  • Simple concepts: 0.5-1s wait
  • Moderate concepts: 2s wait
  • Complex concepts: 4s wait (Jensen's inequality, etc.)
  • Critical insights: 6s wait

Positioning

  • NEVER use magic numbers (LEFT * 3.5)
  • ALWAYS use relative positioning (next_to, move_to with config.frame_width)

Scene Organization

  • ONE concept per scene
  • Use next_section() for complex animations
  • Explicit object tracking for cleanup

Interaction Flow

For Single Scene Creation:

1. What mathematical concept do you want to visualize?
   [probability | calculus | linear algebra | statistics | geometry | custom]

2. Target duration?
   [30 seconds | 60 seconds | 90 seconds]

3. Does it involve:
   - Mathematical formulas? [yes/no]
   - Camera movements (zoom/pan)? [yes/no]
   - Data visualization (plots, graphs)? [yes/no]

4. Complexity level?
   [simple | moderate | complex]

Read the full file on GitHub · 128 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. 3d ago First seen · 128 lines · 39 tokens per session scan A b819691609be

Subscribe to this mod's changes

viz-architect is an agent published in the GitHub repository choxos/MathVizAgent (1 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 959 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

glm-cinematographer

Stage 5 of the GLM chain. Writes the shot list against the curriculum and dossier. Camera grammar is setcameraorientation / movecamera only. Reference images are visual seeds, never teaching sources.

HarleyCoops/Math-To-Manim · 46 tokens

arcgentic-auditor

Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…

Arch1eSUN/Arcgentic · 101 tokens

mojiemoji-selector

Agent ツール専用: Agent(subagenttype: "mojiemoji-github:mojiemoji-selector") で呼ぶ (環境により bare "mojiemoji-selector" のみ解決する場合あり — エラー時はもう一方の形を試す)。Skill ツールではどちらの形も呼べない。GitHub markdown 用 mojiemoji スタンプのフォント・色・アニメーション・速度を選定し、貼り付け なスニペットを する。.

jozobeer/mojiemoji-plugin · 266 tokens

thumbnail-agent

Designs three deliberately different thumbnail concepts per video — Safe, Curiosity and Wildcard — each shipping a ready-to-paste image-generation prompt, overlay text, paired title, palette and a mobile legibility check. Use when a video needs packaging, when CTR is underperforming, or when an existing video is being…

PedroMeloOfficial/Youtube-Agent-Matrix · 84 tokens

polyviz

Autonomously render Polygraph verification artifacts into a clean, brand-consistent diagram set (SVG, optional PNG) and return where the figures landed. Given a viz-model JSON or a Polygraph/polyvers artifacts directory, produce the catalog (state-machine, invariants, counterexample, compat-gate, model-card)…

cognitive-fab/polygraph · 109 tokens

ve-diagram-builder

Build one visual-explainer diagram fragment. Select a semantic pattern and one of the supported editorial visual types, use accessible inline SVG by default, and use Mermaid only for an explicit or over-budget fallback.

theclaymethod/artifacture · 46 tokens