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 skills add dbillion/manim-storytelling-skills --skill manim-explainer-animationsgit clone --depth 1 https://github.com/dbillion/manim-storytelling-skillsWrote 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/skills/dbillion/manim-storytelling-skills/manim-explainer-animations)<a href="https://agentmods.dev/skills/dbillion/manim-storytelling-skills/manim-explainer-animations"><img src="https://agentmods.dev/badge/skills/dbillion/manim-storytelling-skills/manim-explainer-animations/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.
<a href="https://agentmods.dev/skills/dbillion/manim-storytelling-skills/manim-explainer-animations"><img src="https://agentmods.dev/badge/skills/dbillion/manim-storytelling-skills/manim-explainer-animations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00232 | $0.02055 |
| Opus 5 | $0.00116 | $0.01027 |
| Sonnet 5 | $0.00046 | $0.00411 |
| Haiku 4.5 | $0.00023 | $0.00205 |
Grade A, and why
manim-explainer-animations 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manim Explainer Animations (Manim Community Edition, latest stable v0.20.x)
What this skill produces
A produced-feeling explainer sequence, not just technically-correct code: a hook, a build-up, a visual payoff, a release — using the right mobject/animation combination for the idea, not just the first one that works. Treat camera work, color, pacing, and text choices as part of the deliverable.
Always use Manim Community Edition (pip install manim, import as from manim import *), not manimlib (Grant Sanderson's personal fork), unless the user explicitly asks for exact 3b1b source parity. CE is what's documented, pip-installable, and actively maintained.
Setup
pip install manim --break-system-packages
apt-get install -y libcairo2-dev libpango1.0-dev ffmpeg 2>/dev/null || true
python3 -c "import manim; print(manim.__version__)" # confirm before building anything nontrivial
Optional but high-value plugins (check if the task needs them before installing):
pip install manim-voiceover --break-system-packages # narration-synced timing, TTS or recorded audio
pip install manim-physics --break-system-packages # rigid body / fluid / pendulum simulations
Workflow
- Identify the idea's shape before picking mobjects. Is this a transformation (Transform-family), a process over time (updaters/ValueTracker), a relationship (Graph/graph theory), a function (Axes/ParametricFunction), a proof/derivation (MathTex + TransformMatchingTex), or a spatial object (3D mobjects)? The category determines which reference file to read.
- Storyboard in beats (5-8 beats, ~5-20s each): hook → build-up → core demonstration → payoff. Comment each beat in the
construct()method so timing can be adjusted independently later. - Read the relevant reference file(s) below before writing code — don't guess class names or signatures from memory; the API surface is large and easy to misremember (e.g.
ShowCreationwas renamedCreatein CE;TexMobject/TextMobjectwere renamedMathTex/Tex). - Render low-quality first, iterate on timing, then final-render:
manim -pql scene.py SceneName # quick preview, 480p15 manim -pqh scene.py SceneName # 1080p60 final manim -pqk scene.py SceneName # 4K60, only if actually needed - Apply the style-guide conventions (color, camera, pacing) from
references/style-guide.md— don't leave default Manim styling (pure black background, default primary colors) unless the user asked for a plain/utilitarian look.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/4d-math.md 5.1 KB
- references/advanced-techniques.md 5.1 KB
- references/animations.md 6.5 KB
- references/camera-and-scenes.md 4.3 KB
- references/mobjects.md 6.4 KB
- references/plotting-and-graphs.md 3.4 KB
- references/style-guide.md 5.3 KB
- references/text-and-typography.md 4.2 KB
- scripts/algebra_steps_template.py 1.4 KB runs code
- scripts/cheatsheet_scene.py 3.4 KB runs code
- scripts/graphing_template.py 1.9 KB runs code
- scripts/hypersphere_template.py 2.4 KB runs code
- scripts/tesseract_template.py 3.4 KB runs code
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.
- 12d ago First seen · 68 lines · 232 tokens per session scan A 5cf890d4fba7
manim-explainer-animations is a skill published in the GitHub repository dbillion/manim-storytelling-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 232 tokens to every session and 2,055 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…