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 metaspartan/cybara --skill manim-videogit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/manim-video)<a href="https://agentmods.dev/skills/metaspartan/cybara/manim-video"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/manim-video/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/metaspartan/cybara/manim-video"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/manim-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00430 |
| Opus 5.5 | $0.00016 | $0.00172 |
| Sonnet 5.5 | $0.00008 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
manim-video 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 2mo 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.
What it actually says
Manim Video
Manim is an animation engine (Python) for precise mathematical/explanatory videos. Write a scene, render it to MP4 with manim.
When to use
- "animate / make a video showing …"
- Math derivations, algorithm visualizations, geometric constructions.
- Step-by-step explainers.
Workflow
- Write a Python scene file using the Manim API. Save with the
writetool, e.g.scene.py. - Render:
manim -pql scene.py SceneName(low quality preview,-pplays after). Use-pqhfor high quality / final. - Output MP4 lands under
media/videos/.... State the path.
Minimal scene template
from manim import *
class Squares(Scene):
def construct(self):
s = Square(side_length=2, color=BLUE)
self.play(Create(s))
self.play(s.animate.rotate(PI / 2).set_color(RED))
self.wait()
Tips
- Keep scenes short and focused; one idea per scene.
- Animate one property change per
self.play(...)step so it reads clearly. - For text, use
MathTex(LaTeX math) orText(plain). - Prefer
-qlpreviews while iterating; switch to-qhonly for the final render. - Requires
python3and themanimpackage (install via pip). Per project rules, never use npm-equivalents for JS; here Manim is Python so pip is correct.
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.
- 2mo ago First seen · 43 lines · 39 tokens per session scan A 331cc7cce2ef
manim-video is a skill published in the GitHub repository metaspartan/cybara (33 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 430 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
zeroclaw-docs
Use when a user asks how ZeroClaw itself works or requests setup, configuration, diagnostics, capability discovery, extension, or operation of the current ZeroClaw installation. Do not use for ordinary software tasks that merely mention a ZeroClaw concept or repository file. Verify the installed build through live…
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
awesome-ai-agents-curation
Help founders prepare evidence-backed AI agent project submissions and help maintainers triage project issues and pull requests for the Awesome AI Agents list.
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
explain
Explain a concept, system or piece of code as a diagram-first terminal answer, or as an interactive HTML page.
ai-engineering-curriculum
Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.