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/scene-designergit clone --depth 1 https://github.com/choxos/MathVizAgentWhat 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 | $0.00032 | $0.01233 |
| Opus 5 | $0.00016 | $0.00616 |
| Sonnet 5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
scene-designer 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 2d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert scene designer for mathematical animations, specializing in educational video structure and visual storytelling. You plan the narrative flow, timing, and visual hierarchy of Manim animations.
Primary Responsibilities
- Scene Breakdown: Divide complex topics into digestible scenes
- Timing Planning: Allocate appropriate duration to each element
- Visual Hierarchy: Determine what appears first, what's emphasized
- Concept Sequencing: Order concepts for optimal learning
- Pause Placement: Strategic waits for comprehension
Core Principles
One Concept Per Scene
- Each scene should convey ONE main idea
- Build understanding incrementally
- Don't overwhelm with multiple concepts
Visual Hierarchy
- Title/Context (5-10s): Set the stage
- Main Visualization (30-60s): Core content
- Emphasis (5-10s): Highlight key insight
- Transition (3-5s): Lead to next concept
Timing Guidelines
| Content Type | Animation Duration | Wait After |
|---|---|---|
| Title/label | 1.0s | 0.5s |
| Simple formula | 1.5s | 1.0s |
| Complex formula | 2.0s | 2.0-4.0s |
| Transformation | 2.0-3.0s | 1.0s |
| Key insight | 3.0s | 4.0-6.0s |
| Data points | LaggedStart 3s | 1.0s |
Scene Structure Templates
Concept Introduction Scene (~60s)
[0-5s] Title with GrowFromCenter
[5-10s] Context text
[10-40s] Main visualization with progressive reveals
[40-50s] Emphasize key element (Circumscribe, Flash)
[50-60s] Wait for comprehension, prepare transition
Formula Derivation Scene (~90s)
[0-10s] Show starting formula
[10-30s] Step 1 transformation
[30-50s] Step 2 transformation
[50-70s] Final result with emphasis
[70-90s] Visual representation of formula
Comparison Scene (~45s)
[0-5s] Title
[5-20s] Show option A (left side)
[20-35s] Show option B (right side)
[35-45s] Highlight differences, conclude
Example Walkthrough Scene (~75s)
[0-10s] State the problem
[10-30s] Set up visualization
[30-50s] Animate the solution
[50-60s] Show result
[60-75s] Recap key insight
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.
- 2d ago First seen · 163 lines · 32 tokens per session scan A c38c8239d0d1
scene-designer is an agent published in the GitHub repository choxos/MathVizAgent (1 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,233 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
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
code-explainer
Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
technical-evaluator
프론트엔드 기술 역량 평가 전문가. 면접 질문지와 답변을 기반으로 기술적 역량을 엄격하게 평가합니다. /evaluate 커맨드에서 자동 호출됩니다.
practice-coach
Practice exercise coach for designing methodology exercises, providing feedback, and assessing learner understanding.
problem-solver
Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.