grok-intent

grok-intent is an agent for Claude Code from HarleyCoops/Math-To-Manim. It costs 48 tokens per session (527 once invoked), scanned A, original, MIT.

An intent-planning stage for a Grok-based math animation workflow using Manim, a tool for creating mathematical videos. It turns a prompt or photographed homework page into the audience, solved insight, scope, emotional arc, and main visual focus.

In plain words
What is it for?
Use it to interpret a math problem, identify the final claim viewers should understand, choose the key visual zoom, and set the intended audience and runtime.
Why use it?
It helps decide what a math film should communicate before anyone plans scenes, formulas, or code.

Agent for Claude Code

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

Good fit Use it to interpret a math problem, identify the final claim viewers should understand, choose the key visual zoom, and set the intended audience and runtime.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/harleycoops/math-to-manim/grok-intent
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 · 2,569 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 grok-intent

README.md
[![agentmods](https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-intent.svg)](https://agentmods.dev/agents/harleycoops/math-to-manim/grok-intent)
Your own site
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/grok-intent"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-intent.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 527 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 $0.00048 $0.00527
Opus 5 $0.00024 $0.00264
Sonnet 5 $0.00010 $0.00105
Haiku 4.5 $0.00005 $0.00053

Measured 8d ago against content hash 6e6580888d43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

grok-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 8d 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.

grok/agents/grok-intent.md · 45 lines

What it actually says

You are the Intent stage of the Grok-native Math To Manim chain. You decide what the film is about. Not its shots. Not its formulas. The solved insight.

THINKING CONTRACT

  • Work from the viewer's mind, not from a topic catalog.
  • 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 a spatial object and the claim becomes visible.

ALLOWED TOOLS

  • None. Vision is input, not a tool. Do not search. Do not write code.
  • Do not call web_search, x_search, code_interpreter, or image_generation.

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: if an image was attached, the transcribed givens, unknown, and diagram notes; otherwise null.

FORBIDDEN MOVES

  • Do not write Manim, Python, or a lesson plan.
  • Do not solve the homework here. Solving belongs to math-director and its sandbox.
  • 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.

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. 8d ago First seen · 45 lines · 48 tokens per session scan A 6e6580888d43

Subscribe to this mod's changes

grok-intent is an agent published in the GitHub repository HarleyCoops/Math-To-Manim (2,569 stars, last pushed 10d ago), licensed MIT. It adds 48 tokens to every session and 527 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 2026-08-30.