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.
git clone --depth 1 https://github.com/shihabshahrier/manim-coding-skillWrote 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/plugins/shihabshahrier/manim-coding-skill/gemini-extension)<a href="https://agentmods.dev/plugins/shihabshahrier/manim-coding-skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/shihabshahrier/manim-coding-skill/gemini-extension/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/plugins/shihabshahrier/manim-coding-skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/shihabshahrier/manim-coding-skill/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
test-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 yesterday.
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
{
"name": "test-manim",
"description": "Create teaching-quality STEM animations with ManimGL. Narrative-driven, chunk-based, works with any AI model.",
"version": "1.0.0",
"contextFileName": "GEMINI.md"
}
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.
- yesterday First seen · 7 lines scan A 602bf75ec878
test-manim is a plugin published in the GitHub repository shihabshahrier/manim-coding-skill (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-09.
Other plugins, from other repositories
shumo-paper
A Chinese-language assistant for the National College Students Mathematical Modeling Competition. It covers problem analysis, model selection, data preparation, solving, result checks, and writing the competition paper.
knot-theory-educator
'Expert in visualizing and explaining braid theory, knot mathematics, and topological concepts for educational purposes. Use for creating interactive visualizations, explainer cards, step-wise animations, and translating abstract algebra into intuitive understanding. Activate on keywords: braid theory, knot…
hypha
Hypha is the AI agent of the Mycelium ecosystem: a connecting filament between engineers and the SysML v2 specification. Provides skills and subagents for KerML/SysML v2 metamodel lookup, standard model library lookup, normative spec citation, and SysML v2 textual-notation validation.
claude-teacher-marketplace
Personal-tutor plugins for Claude Code — adaptive teaching, knowledge tracking, and spaced repetition.
talk-to-anyone
Turn any public figure into your personal coach, living or historical. /coach researches the person across the web, pulls real transcripts when they have video anywhere on YouTube, builds a persona, and talks to you as them until you switch or end.
quiz-me
Gates code changes behind an interactive quiz: Claude investigates, tests your understanding of root cause and fix, and only implements once you pass.