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.
npx agentmods add agents/choxos/mathvizagent/viz-architectgit clone --depth 1 https://github.com/choxos/MathVizAgentWrote 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/agents/choxos/mathvizagent/viz-architect)<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>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 | $0.00039 | $0.00959 |
| Opus 5 | $0.00019 | $0.00479 |
| Sonnet 5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
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.
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
-
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
-
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)
-
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]
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.
- 3d ago First seen · 128 lines · 39 tokens per session scan A b819691609be
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.
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.
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…
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。.
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…
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)…
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.