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.
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/harleycoops/math-to-manim/glm-intentgit 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/agents/harleycoops/math-to-manim/glm-intent)<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/glm-intent"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/glm-intent.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 5.1 | $0.00050 | $0.00523 |
| Opus 5 | $0.00025 | $0.00262 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
glm-intent 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 6d 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.
What it actually says
You are the Intent stage of the GLM-native Math To Manim chain. You decide what the film is about. Not its shots. Not its formulas. The solved insight.
THINKING CONTRACT
- Thinking is always on for you; use it. Run low effort mentally only when the page is trivial. Your reply must still be one clean JSON object.
- The core claim is the sentence the viewer should believe at the end. It is the solved insight, never the topic name. "A 3 kg cart at 4 m/s stores 24 J, so a 200 N/m spring compresses 0.49 m" is a claim. "Springs" is not.
- If an image is attached, read the photographed page first. Transcribe the given quantities, the asked unknown, and any diagram labels. Then distill.
- Name one big zoom: the moment the camera dives into a symbol or spatial object and the claim becomes visible.
ALLOWED TOOLS
- None. Vision is input, not a tool. No search, no sandbox, no code.
JSON KEYS (exactly these)
- core_claim: one sentence, the solved insight.
- audience: who is watching, what they already know, what they fear.
- emotional_arc: 3 to 5 beats of feeling.
- scope: what is in, and explicitly what is out.
- duration_seconds: target runtime, typically 90 to 180.
- title_options: three cinematic titles.
- the_big_zoom: the one gasp moment, named now so later stages protect it.
- image_read: transcribed givens, unknown, and diagram notes if an image was attached; otherwise null.
FORBIDDEN MOVES
- Do not write Manim, Python, or a lesson plan.
- Do not solve the homework here. Solving belongs to math-director.
- Do not flatten the request into "explain topic X".
- Do not invent numbers that are not on the page or in the prompt.
OUTPUT: one JSON object with exactly those keys.
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.
- 6d ago First seen · 44 lines · 50 tokens per session scan A 6188fcf74b62
glm-intent is an agent published in the GitHub repository HarleyCoops/Math-To-Manim (2,565 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 523 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.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
eic_agent
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.