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 graniet/kheish --skill manim-videogit clone --depth 1 https://github.com/graniet/kheishWrote 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/graniet/kheish/manim-video)<a href="https://agentmods.dev/skills/graniet/kheish/manim-video"><img src="https://agentmods.dev/badge/skills/graniet/kheish/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/graniet/kheish/manim-video"><img src="https://agentmods.dev/badge/skills/graniet/kheish/manim-video.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 | $0.00083 | $0.03185 |
| Opus 5.5 | $0.00033 | $0.01274 |
| Sonnet 5.5 | $0.00017 | $0.00637 |
| Haiku 4.5 | $0.00008 | $0.00318 |
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.
This is a copy
89% identical to manim-video — 30 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kheish Compatibility
This skill is repo-local and stays inactive until explicitly activated.
When the original instructions refer to legacy tool names, use these Kheish mappings:
terminal=>bashweb_extract=>web_fetch, plusweb_searchwhen discovery is neededsearch_files=>grep_searchandglob_searchbrowser_*tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly
When the instructions mention local helper files, resolve them from ${KHEISH_SKILL_DIR}.
Manim Video Production Pipeline
Creative Standard
This is educational cinema. Every frame teaches. Every animation reveals structure.
Before writing a single line of code, articulate the narrative arc. What misconception does this correct? What is the "aha moment"? What visual story takes the viewer from confusion to understanding? The user's prompt is a starting point — interpret it with pedagogical ambition.
Geometry before algebra. Show the shape first, the equation second. Visual memory encodes faster than symbolic memory. When the viewer sees the geometric pattern before the formula, the equation feels earned.
First-render excellence is non-negotiable. The output must be visually clear and aesthetically cohesive without revision rounds. If something looks cluttered, poorly timed, or like "AI-generated slides," it is wrong.
Opacity layering directs attention. Never show everything at full brightness. Primary elements at 1.0, contextual elements at 0.4, structural elements (axes, grids) at 0.15. The brain processes visual salience in layers.
Breathing room. Every animation needs self.wait() after it. The viewer needs time to absorb what just appeared. Never rush from one animation to the next. A 2-second pause after a key reveal is never wasted.
Cohesive visual language. All scenes share a color palette, consistent typography sizing, matching animation speeds. A technically correct video where every scene uses random different colors is an aesthetic failure.
What ships with it
16 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.
- README.md 886 B
- references/animation-design-thinking.md 7.0 KB
- references/animations.md 8.6 KB
- references/camera-and-3d.md 4.0 KB
- references/decorations.md 4.9 KB
- references/equations.md 5.9 KB
- references/graphs-and-data.md 4.5 KB
- references/mobjects.md 9.5 KB
- references/paper-explainer.md 9.1 KB
- references/production-quality.md 5.8 KB
- references/rendering.md 5.2 KB
- references/scene-planning.md 2.7 KB
- references/troubleshooting.md 4.2 KB
- references/updaters-and-trackers.md 8.3 KB
- references/visual-design.md 4.7 KB
- scripts/setup.sh 921 B 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.
- 2mo ago First seen · 282 lines · 83 tokens per session scan A 42f38b3125fa
manim-video is a skill published in the GitHub repository graniet/kheish (218 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 3,185 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to manim-video, differing in 30 lines, and is treated as a copy.
Other skills, from other repositories
study-plan
A long-term study planner that divides learning into stages and adapts the schedule using practice results. It can also plan focused practice sessions for a specific number of questions or flashcards.
outline-builder
A study aid that helps build an outline from a learner's notes, textbook excerpts, or an existing outline. It creates the structure and leaves gaps for the learner to fill rather than writing the lesson for them.
exam-forecast
An exam-pattern guide that compares several past papers from the same teacher or course. It identifies recurring topics, question formats, common traps, and changes over time, then estimates which areas may deserve more study.
flashcards
A lightweight flashcard and review method for learning facts and concepts in a conversation. It uses Leitner boxes, a simple system that shows cards at increasing intervals as they are remembered.
weak-point-drill
A targeted practice workflow that finds the topics a learner repeatedly gets wrong and gives those topics more questions. It explains answers and tracks recurring mistakes across practice sessions.
product-help
Answer questions about how to use octo, or diagnose something that isn't working, by reading the product documentation. Use when the user asks "how do I...", "what is...", "where is the docs for...", any usage/help question about octo itself, or reports a problem — "not working", "won't start", "error", "connection…