hermes-learns-manim

hermes-learns-manim is a skill for Codex from HarleyCoops/Math-To-Manim. It costs 42 tokens per session (878 once invoked), scanned A, original, MIT.

A workflow for creating and checking Manim animations, which are program-generated videos that explain mathematics.

In plain words
What is it for?
Use it to inspect files, generate animation code, run checks, render videos, and review selected frames in the Math-To-Manim project.
Why use it?
It keeps animation work organized and checks results before rendering, reducing mistakes in educational math videos.

Skill for Codex

Written for Codex: runs codex exec. Also seen: mentions AGENTS.md; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./.venv/bin/python -m math_to_manim.cli --help.

Good fit Use it to inspect files, generate animation code, run checks, render videos, and review selected frames in the Math-To-Manim project.

Compare 6 skills from other repositories ↓
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 · 2,583 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HarleyCoops/Math-To-Manim
agentmods
npx agentmods add skills/harleycoops/math-to-manim/hermes-learns-manim

Made for: Codex.

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 hermes-learns-manim

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/harleycoops/math-to-manim/hermes-learns-manim"><img src="https://agentmods.dev/badge/skills/harleycoops/math-to-manim/hermes-learns-manim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 878 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Excessive Agency · line 53
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00042 $0.00878
Opus 5 $0.00021 $0.00439
Sonnet 5 $0.00008 $0.00176
Haiku 4.5 $0.00004 $0.00088

Measured 11d ago against content hash 92d55d11695e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hermes-learns-manim 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 11d 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.

archive/hermes/hermes/skills/hermes-learns-manim/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Learns Manim

Use this skill when operating the Math-To-Manim repo with Hermes to inspect, generate, validate, render, or review educational Manim animations.

Operating Contract

  • Read README.md and AGENTS.md before editing.
  • Treat Hermes as contributor tooling, not a Python runtime dependency.
  • Keep M2M2 artifacts inspectable under runs/<run_id>/.
  • Keep user-visible render/demo outputs in repo-local runs/; use .tmp-runs/ only for disposable smoke checks, and do not send user-facing movies to /tmp.
  • Preserve the pipeline contract: story before symbols, geometry before algebra, artifacts before side effects.
  • Prefer deterministic no-render checks before model-backed or render-heavy runs.
  • Do not commit generated runs/, media/, temporary renders, secrets, or local caches.
  • For showcase/media changes, visually inspect representative frames/GIFs before claiming success.

Quick Verification

From the repo root:

./.venv/bin/python -m math_to_manim.cli --help
./.venv/bin/python -m math_to_manim.cli generate --help
./.venv/bin/python -m math_to_manim.cli generate "Explain why derivatives are slopes" --deterministic --no-render --runs-dir .tmp-runs/m2m2-smoke

If the venv is not installed yet:

python3 -m venv .venv
./.venv/bin/python -m pip install -U pip
./.venv/bin/python -m pip install -e ".[dev]"

For Codex-backed code generation, first verify the local Codex CLI:

codex --version
codex exec "Say ready from inside this repo"

Starter Workflow

  1. Inspect pyproject.toml, math_to_manim/cli.py, and math_to_manim/pipeline/runner.py.
  2. Run CLI help or a deterministic smoke command before changing behavior.
  3. Open the generated runs/<run_id>/ bundle and inspect JSON artifacts before changing downstream code.
  4. For media work, render only after static validation passes and inspect the output visually.
  5. Report exact commands, run bundle paths, skipped checks, and changed files.

Read the full file on GitHub · 91 lines

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. 11d ago First seen · 91 lines · 42 tokens per session scan A 92d55d11695e

Subscribe to this mod's changes

hermes-learns-manim is a skill published in the GitHub repository HarleyCoops/Math-To-Manim (2,583 stars, last pushed 14d ago), licensed MIT. It adds 42 tokens to every session and 878 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 skills, from other repositories

html-ppt-zhangzara-monochrome

A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.

nexu-io/open-design · 54 tokens

html-ppt-zhangzara-pin-and-paper

A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.

nexu-io/open-design · 51 tokens

paper-illustration

A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

paper-illustration-image2

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.

wanshuiyin/Auto-claude-code-research-in-sleep · 59 tokens

paper2video

Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video by fully delegating slide authoring to the installed ppt-master skill and fully delegating rendering, subtitles, timeline assembly, and strict media QA to the installed pptx2video skill and its public CLI. Resolves one…

microsoft/ResearchStudio · 157 tokens

figure-composer

Compose one publication-grade multi-panel figure. Start from a one-line claim plus immutable data Artifact Version references, or inspect an existing figure and draft its outline directly. Plan a 12-column panel outline, delegate one worker per panel, compose and inspect the result, then run at most three adversarial…

aipoch/open-science · 93 tokens