glm-math-director

glm-math-director is an agent for Claude Code from HarleyCoops/Math-To-Manim. It costs 56 tokens per session (456 once invoked), scanned A, original, MIT.

A math-and-physics checking agent for a GLM-to-Manim workflow, where Manim is software for creating mathematical animations.

In plain words
What is it for?
Use it to solve quantities symbolically and numerically, check units, break formulas into explainable LaTeX parts, document terms, and keep symbol colors consistent across an animation.
Why use it?
It helps catch incorrect calculations, units, formulas, and animation labels before numbers appear on screen.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to solve quantities symbolically and numerically, check units, break formulas into explainable LaTeX parts, document terms, and keep symbol colors consistent across an animation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/harleycoops/math-to-manim/glm-math-director
About the project

Math To Manim turns questions about mathematics or physics into checked visual explanations and rendered Manim animations. It is intended for learners who want concepts explained through ordered reasoning, notes, and motion. Catalogue add-ons provide agents that create and support these explainers.

HarleyCoops/Math-To-Manim · 2,573 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/HarleyCoops/Math-To-Manim

Made for: Claude Code.

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 glm-math-director

README.md
[![agentmods](https://agentmods.dev/badge/agents/harleycoops/math-to-manim/glm-math-director/github.svg)](https://agentmods.dev/agents/harleycoops/math-to-manim/glm-math-director)
Your own site
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/glm-math-director"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/glm-math-director/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for glm-math-director

Your own site · 80×15
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/glm-math-director"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/glm-math-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00056 $0.00456
Opus 5 $0.00028 $0.00228
Sonnet 5 $0.00011 $0.00091
Haiku 4.5 $0.00006 $0.00046

Measured 9d ago against content hash eb3a0e283726, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

glm-math-director 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 9d 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.

glm/agents/glm-math-director.md · 43 lines

What it actually says

You are the Math Director of the GLM-native Math To Manim chain. Numbers that appear on screen must be earned twice: once by derivation, once by check.

THINKING CONTRACT

  • Think at high effort by default; raise to max whenever units disagree or a number looks lucky rather than derived.
  • Solve every asked quantity symbolically first, then numerically.
  • Check units dimension by dimension. An animation cannot hide a bad unit.
  • Decompose each displayed formula into latex_parts small enough that each part can be highlighted alone. Gloss every part in plain words.
  • Assign each recurring symbol a color identity so the palette stays consistent across acts.
  • If a sandbox is available on the platform, run the arithmetic there and say so in checks. If it is not available, run it in thinking and mark checks accordingly. Never silently skip verification.

ALLOWED TOOLS

  • code_interpreter / sandbox when the platform offers it: computations only.
  • Search only for cited physical constants with their values.

JSON KEYS (exactly these)

  • formulas: list of {id, act_number, latex_parts, term_glossary, derivation_or_motivation, common_misreading}.
  • color_identity: map of symbol to named meaning.
  • numbers: every value the film will show, with {name, value, units, source}.
  • checks: what you verified and how.
  • sources: constants and references used.

FORBIDDEN MOVES

  • Do not change the core claim or curriculum.
  • Do not show a number without a source line in numbers[].
  • Do not write LaTeX you have not glossed word for word.
  • Do not write shots or scene code.

OUTPUT: one JSON object with exactly those keys.

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. 9d ago First seen · 43 lines · 56 tokens per session scan A eb3a0e283726

Subscribe to this mod's changes

glm-math-director is an agent published in the GitHub repository HarleyCoops/Math-To-Manim (2,573 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 456 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

domain-reviewer

Substantive domain review for lecture slides. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.

pedrohcgs/claude-code-my-workflow · 56 tokens

book-author

Creates and manages scientific book projects in PaperLab. Handles the full lifecycle: project scaffolding, chapter writing with LaTeX equations, notebook creation for computational figures, book building, and rendering to HTML/Word/PDF/ODF. Does NOT handle paper writing — use the scientific-writer agent for papers.

equinor/neqsim · 66 tokens

case-thread-continuity-editor

Tracks recurring cases across a PaperLab book and prevents assumptions, numbers, names, and teaching roles from drifting unintentionally.

equinor/neqsim · 31 tokens

interactive-lab-designer

Converts selected static PaperLab notebooks into safe, student-facing interactive HTML labs with static fallbacks for PDF and print formats.

equinor/neqsim · 31 tokens

paper-to-book-synthesizer

Converts validated PaperLab papers into book chapters, textbook sections, worked examples, exercises, notebooks, and figure discussions.

equinor/neqsim · 32 tokens

worked-example-factory

Builds polished worked examples from PaperLab equations, notebooks, benchmark results, and case studies, including givens, assumptions, solution steps, and checks.

equinor/neqsim · 36 tokens