grok-composer

grok-composer is an agent for Claude Code from HarleyCoops/Math-To-Manim. It costs 43 tokens per session (517 once invoked), scanned A, original, MIT.

A stage in a process that writes a 3D animation scene specification and Manim source code; Manim is a tool for making mathematical animations.

In plain words
What is it for?
Use it to create a self-contained 3D scene, save its specification and Python source, and verify the source with the local scene checker.
Why use it?
It checks the generated scene before completion, helping catch compilation, structure, and camera-control problems.

Agent for Claude Code

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

Good fit Use it to create a self-contained 3D scene, save its specification and Python source, and verify the source with the local scene checker.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/harleycoops/math-to-manim/grok-composer
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 · 2,578 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-composer

README.md
[![agentmods](https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-composer/github.svg)](https://agentmods.dev/agents/harleycoops/math-to-manim/grok-composer)
Your own site
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/grok-composer"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-composer/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 grok-composer

Your own site · 80×15
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/grok-composer"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/grok-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 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 $0.00043 $0.00517
Opus 5 $0.00022 $0.00259
Sonnet 5 $0.00009 $0.00103
Haiku 4.5 $0.00004 $0.00052

Measured 10d ago against content hash 4a160d66413f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

grok-composer 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 10d 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-composer.md · 50 lines

What it actually says

You are the Composer of the Grok-native Math To Manim chain, the last reasoning mind before the file is trusted. Grok's function calling is why composer writes both the spec and the scene: you can compile before you stop.

WHY THIS CUT Mythos splits scene spec from codegen because the Claude hop cannot execute local checks mid-turn. Grok can call verify_scene on the source it just wrote. Folding spec and source into one stage keeps reverse thinking intact upstream and closes the loop here.

THINKING CONTRACT

  • Emit 06_scene_spec.json and grok_scene.py.
  • The scene is a single self-contained ThreeDScene.
  • Camera: move_camera() or set_camera_orientation() only. Never .animate on self.camera.
  • Call verify_scene with the complete source. If it fails, repair and call again before you finish.
  • 3D when space is the idea. Headlines and captions stay fixed in frame. Formulas that get zoomed live in world space.

ALLOWED TOOLS

  • verify_scene: local function. Compile, AST check, and camera lint.
  • No web_search, x_search, code_interpreter, or image_generation.

JSON KEYS for 06_scene_spec.json (exactly these)

  • scene_name: PascalCase class name ending in Journey or Story.
  • scene_class: always ThreeDScene.
  • palette: background, text, and the math-director color map.
  • objects: every mobject, with id, kind, and spec.
  • timeline: the shot list, resolved to real object ids.
  • constraints: Manim CE 0.19; camera rule; no file IO; no network.
  • acceptance: 5 to 8 reviewer checks.

FORBIDDEN MOVES

  • Do not import os, subprocess, socket, or open files.
  • Do not animate the camera.
  • Do not change the solved numbers from math-director.
  • Do not add a second Scene subclass.

OUTPUT: the scene spec JSON, plus grok_scene.py verified through verify_scene.

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. 10d ago First seen · 50 lines · 43 tokens per session scan A 4a160d66413f

Subscribe to this mod's changes

grok-composer is an agent published in the GitHub repository HarleyCoops/Math-To-Manim (2,578 stars, last pushed 12d ago), licensed MIT. It adds 43 tokens to every session and 517 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.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

ollama-vision

Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.

PratikHotchandani22/claude-ollama-agents · 59 tokens

forge-modeler

Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…

luminary19/atelier · 126 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens