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 shihabshahrier/manim-coding-skill --skill test-manimgit 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/skills/shihabshahrier/manim-coding-skill/test-manim)<a href="https://agentmods.dev/skills/shihabshahrier/manim-coding-skill/test-manim"><img src="https://agentmods.dev/badge/skills/shihabshahrier/manim-coding-skill/test-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.
<a href="https://agentmods.dev/skills/shihabshahrier/manim-coding-skill/test-manim"><img src="https://agentmods.dev/badge/skills/shihabshahrier/manim-coding-skill/test-manim.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 | $0.00092 | $0.02776 |
| Opus 5 | $0.00046 | $0.01388 |
| Sonnet 5 | $0.00018 | $0.00555 |
| Haiku 4.5 | $0.00009 | $0.00278 |
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 8d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ManimGL STEM Animation Skill
Produce pedagogically-effective STEM teaching animations: narrative-first, chunk-based (15s segments), rendered in ManimGL (manimgl v1.7+), merged into one final video.
Invocation
/test-manim "Newton's Laws of Motion"
/test-manim "Fourier Series" --duration 60
/test-manim "Neural Networks" --duration 90 --model minimax
| Arg | Default | Values |
|---|---|---|
| topic | required | any STEM subject string |
| --duration | 30 | 30, 60, 90, 120 (seconds) |
| --model | session model | identifier used in folder name |
Phase 0 — Parse & Scaffold
Extract from invocation:
TOPIC— subject string (required)DURATION— total seconds (default: 30)MODEL_NAME— folder identifier (default: derive from session context or use "claude")CHUNK_COUNT= ceil(DURATION / 15)TOPIC_SLUG= TOPIC lowercased, spaces→underscores, strip special chars
Create project at current working directory:
manim-{MODEL_NAME}/
{TOPIC_SLUG}/
scenes/
chunk_01_{name}.py
chunk_02_{name}.py
...
output/
chunks/
final/
assets/
SCENE_PLAN.md
render.sh
merge.sh
Create all directories with mkdir -p before writing any files.
Make render.sh and merge.sh executable with chmod +x.
Phase 1 — Narrative Planning (ALWAYS before code)
Write SCENE_PLAN.md completely before writing any .py files.
Story Arc Requirements
Every animation must have:
- Hook (first chunk): One striking visual that poses the core question
- Build (middle chunks): One concept per chunk, each building on prior
- Resolution (last chunk): Visual synthesis connecting all prior chunks; key insight held on screen
SCENE_PLAN.md Template
# {TOPIC} — Animation Plan
**Duration**: {DURATION}s | **Chunks**: {CHUNK_COUNT} × 15s | **Model**: {MODEL_NAME}
## Story Arc
- Hook: [striking opening visual — what question does it pose?]
- Build: [ordered list of concepts, one per chunk]
- Resolution: [final synthesis — what understanding has the viewer gained?]
## Visual Language
- Background: BLACK
- Primary concept color: BLUE
- Secondary concept color: YELLOW
- Accent / highlight: RED or GREEN
- Text / labels: WHITE
- Rule: one color = one concept, consistent across ALL chunks
## Chunks
### Chunk 1 — {name} (0s–15s)
- Role: Hook
- Concept: [what is demonstrated]
- Opening: [first visual the viewer sees]
- Key moment: [the reveal or insight at ~10s]
- Closing: [held frame at 15s — clean fade out]
- ManimGL objects: [list specific classes]
- Equations: [LaTeX strings if any]
### Chunk 2 — {name} (15s–30s)
- Role: Build
- Concept: ...
[repeat for each chunk]
### Chunk {CHUNK_COUNT} — {name} ({DURATION-15}s–{DURATION}s)
- Role: Resolution
- Concept: ...
- Callback: [reference to visuals from chunk 1]
## Issues Log
[fill during render phase]
What ships with it
2 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.
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.
- 8d ago First seen · 354 lines · 92 tokens per session scan A 4e3abc2f5c26
test-manim is a skill published in the GitHub repository shihabshahrier/manim-coding-skill (2 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 2,776 once invoked, about $0.0005 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
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
c2pa-metadata
Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…
ernie-image
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT…