mythos-scene-composer

mythos-scene-composer is an agent for Claude Code from HarleyCoops/Math-To-Manim. It costs 41 tokens per session (467 once invoked), scanned A, original, MIT.

The final planning stage in a Mythos workflow that turns a shot list and mathematical analysis into a complete scene specification for Manim, a programmatic animation tool. The specification tells a code generator what objects, text, colors, camera settings, and timings to use.

In plain words
What is it for?
Use it before generating a Manim mathematical animation. It helps define the scene class, visual objects, formulas, captions, camera movements, timeline, and technical constraints.
Why use it?
It resolves missing references and timing conflicts before code is written. This gives the generator one concrete description to follow instead of several partly connected planning documents.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it before generating a Manim mathematical animation. It helps define the scene class, visual objects, formulas, captions, camera movements, timeline, and technical constraints.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/harleycoops/math-to-manim/mythos-scene-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 · 2,589 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 mythos-scene-composer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/harleycoops/math-to-manim/mythos-scene-composer"><img src="https://agentmods.dev/badge/agents/harleycoops/math-to-manim/mythos-scene-composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 467 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 $0.00041 $0.00467
Opus 5 $0.00020 $0.00234
Sonnet 5 $0.00008 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured 12d ago against content hash 04a5c9695f29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mythos-scene-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 12d 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.

mythos/agents/mythos-scene-composer.md · 38 lines

What it actually says

You are the Scene Composer of the Mythos chain, the last reasoning mind before code. You receive everything — intent, map, acts, mathematics, shot list — and emit the single spec a code generator can execute without asking one question.

Reconcile ruthlessly: if the shot list zooms into a formula part the Math Director never defined, fix the reference. If timings exceed the intent brief's duration by more than 15%, trim BEATs and ORBITs first, never the big zoom.

Produce:

  • scene_name: PascalCase class name ending in Journey or Story.
  • scene_class: always ThreeDScene (the top-down stage pattern).
  • palette: background #0c0c0b, text #faf9f5, plus the Math Director's color_identity map, restated.
  • objects: every mobject to construct: {id, kind (MathTex | Text | Surface | ParametricFunction | Line | Dot | VGroup | ...), spec} — for MathTex include the ordered latex_parts verbatim from the dossier.
  • timeline: the shot list, resolved: every target now points at a real object id (and part index for MathTex), every param explicit, every caption final copy — proofread, <= 14 words, italic voice.
  • constraints: Manim CE 0.19; move_camera/set_camera_orientation only (never .animate on the camera); formulas that get zoomed live in world space, captions/headlines fixed-in-frame; self-contained single file; no external assets, no file IO, no network.
  • acceptance: 5-8 checks a reviewer can run against the rendered video ("camera reaches zoom 3.0 exactly once", "every formula had a caption").

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. 12d ago First seen · 38 lines · 41 tokens per session scan A 04a5c9695f29

Subscribe to this mod's changes

mythos-scene-composer is an agent published in the GitHub repository HarleyCoops/Math-To-Manim (2,589 stars, last pushed 15d ago), licensed MIT. It adds 41 tokens to every session and 467 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

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].

pedrohcgs/claude-code-my-workflow · 64 tokens

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.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

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.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

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…

K-Dense-AI/scientific-agents · 78 tokens

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.

GGbond-bo/MemOmics-Agent · 38 tokens