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 instructions/harleycoops/math-to-manim/examplesgit clone --depth 1 https://github.com/HarleyCoops/Math-To-ManimWrote 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/instructions/harleycoops/math-to-manim/examples)<a href="https://agentmods.dev/instructions/harleycoops/math-to-manim/examples"><img src="https://agentmods.dev/badge/instructions/harleycoops/math-to-manim/examples.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 | $0.01784 | $0.01784 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
Math-To-Manim examples.instructions.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 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animation Examples Guidelines
Purpose
This directory contains 55+ working Manim animations demonstrating various mathematical, physical, and computational concepts. Each animation serves as both a working example and educational reference.
Creating New Animation Examples
File Organization
- Place animations in the appropriate category directory:
examples/physics/- Physics concepts (quantum, gravity, nuclear, particle physics)examples/mathematics/- Math concepts (geometry, analysis, fractals, statistics)examples/computer_science/- CS concepts (ML, algorithms, spatial reasoning)examples/cosmology/- Cosmology and astrophysicsexamples/finance/- Financial mathematicsexamples/misc/- Experimental or uncategorized
Naming Conventions
- Use descriptive, lowercase names with underscores:
schrodinger_equation.py, notscene1.py - Name should clearly indicate the concept being visualized
- Scene class name should be descriptive and in PascalCase:
SchrodingerEquationScene
Required Components
- Module Docstring: Every animation file must start with a comprehensive docstring:
"""
Visualization of the Schrödinger equation in quantum mechanics.
Shows:
- Wave function evolution
- Probability density interpretation
- Energy eigenstates
- Potential well scenarios
Mathematical Concepts:
- Time-independent Schrödinger equation: Hψ = Eψ
- Time-dependent form: iℏ ∂ψ/∂t = Hψ
- Wave function normalization
- Expectation values
Generated using: Claude Sonnet 4.5 / DeepSeek R1 / etc.
"""
- Import Organization:
from manim import *
import numpy as np
# Other standard library imports
# Then project-specific imports if needed
- Scene Class with Docstring:
class SchrodingerEquationScene(Scene):
"""
Main scene for Schrödinger equation visualization.
Demonstrates wave function evolution in a potential well.
"""
def construct(self):
# Implementation
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.
- 4d ago First seen · 223 lines · 1,784 tokens per session scan A 87d953d5db20
Math-To-Manim examples.instructions.md is an instructions file published in the GitHub repository HarleyCoops/Math-To-Manim (2,557 stars, last pushed 6d ago), licensed MIT. It adds 1,784 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
manim-coding-skill copilot-instructions.md
Instructions for shihabshahrier/manim-coding-skill: When user says /test-manim or asks to create a STEM animation, follow the skill at skills/test-manim/SKILL.md.
manim-coding-skill AGENTS.md
Instructions for shihabshahrier/manim-coding-skill, a project described as: AI STEM animation skill — ManimGL for coding agents.
manim-coding-skill GEMINI.md
Instructions for shihabshahrier/manim-coding-skill, a project described as: AI STEM animation skill — ManimGL for coding agents.
shannon-prover CLAUDE.md
Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.
uniprot-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/uniprot-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.