review-animation

review-animation is a command for coding agents from choxos/MathVizAgent. It costs 14 tokens per session (1,676 once invoked), scanned A, original, MIT.

A checklist and reporting workflow for reviewing Manim code, where Manim is a Python tool for mathematical animations. It checks layout, timing, colors, object cleanup, scene structure, and code reuse.

In plain words
What is it for?
Use it to review existing animation scenes, identify critical issues and warnings, and receive actionable improvements for code and presentation quality.
Why use it?
It helps find production problems that can make an animation confusing, fragile, or difficult to maintain.

Command

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 commands/choxos/mathvizagent/review-animation
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 review-animation

README.md
[![agentmods](https://agentmods.dev/badge/commands/choxos/mathvizagent/review-animation.svg)](https://agentmods.dev/commands/choxos/mathvizagent/review-animation)
Your own site
<a href="https://agentmods.dev/commands/choxos/mathvizagent/review-animation"><img src="https://agentmods.dev/badge/commands/choxos/mathvizagent/review-animation.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,676 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 $0.00014 $0.01676
Opus 5 $0.00007 $0.00838
Sonnet 5 $0.00003 $0.00335
Haiku 4.5 $0.00001 $0.00168

Measured 4d ago against content hash 599cd6214900, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-animation 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 4d 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/commands/review-animation.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review-animation - Code Review Workflow

Review existing Manim animation code for production quality standards and provide actionable improvements.

Workflow Steps

Step 1: Code Submission

User provides their Manim code for review.

Step 2: Automated Analysis (@code-reviewer)

Analyze the code against the following checklist:

Critical Issues (Must Fix)
  • Magic numbers in positioning
  • Missing waits after complex content
  • Inconsistent or excessive colors (>5)
  • No object tracking for cleanup
  • Using FadeOut(*self.mobjects)
  • Wrong scene type for camera work
Warnings (Should Fix)
  • No next_section() in long scenes
  • Multiple concepts in single scene
  • Animations too fast (<0.5s run_time)
  • No semantic color system
  • Repeated code that should be components
  • Hardcoded text sizes
Suggestions (Nice to Have)
  • Could use LaggedStart instead of loop
  • Custom component would improve readability
  • Rate function could enhance feel
  • Camera work could improve focus

Step 3: Generate Review Report

## Code Review: [Scene/File Name]

### Summary
| Metric | Value |
|--------|-------|
| Quality Score | [A/B/C/D] |
| Critical Issues | [count] |
| Warnings | [count] |
| Suggestions | [count] |
| Lines of Code | [count] |

### Critical Issues

#### 1. [Issue Title] (line X)

**Current Code**:
```python
element.shift(LEFT * 3.5)

Problem: Magic number makes code brittle and unclear.

Fix:

element.move_to(LEFT * config.frame_width / 4)

Warnings

1. [Warning Title] (line Y)

Current Code:

self.play(Write(complex_formula))
# Next animation immediately

Problem: No time for viewer to comprehend complex formula.

Recommendation: Add wait after complex content.

self.play(Write(complex_formula), run_time=2)
self.wait(4)  # Time to comprehend

Suggestions

1. [Suggestion Title] (lines A-B)

Current Pattern:

for item in items:
    self.play(Write(item), run_time=0.5)

Improved Pattern:

self.play(LaggedStart(*[Write(item) for item in items], lag_ratio=0.1), run_time=3)

Benefit: Smoother animation, single render pass, professional feel.


Refactored Code

If requested, provide complete refactored version:

Read the full file on GitHub · 290 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. 4d ago First seen · 290 lines · 14 tokens per session scan A 599cd6214900

Subscribe to this mod's changes

review-animation is a command published in the GitHub repository choxos/MathVizAgent (1 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 1,676 once invoked, about $0.0001 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.