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 surajssd/dotfiles --skill manim-videogit clone --depth 1 https://github.com/surajssd/dotfilesWrote 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/surajssd/dotfiles/manim-video)<a href="https://agentmods.dev/skills/surajssd/dotfiles/manim-video"><img src="https://agentmods.dev/badge/skills/surajssd/dotfiles/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/surajssd/dotfiles/manim-video"><img src="https://agentmods.dev/badge/skills/surajssd/dotfiles/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 | $0.00114 | $0.03043 |
| Opus 5.5 | $0.00046 | $0.01217 |
| Sonnet 5.5 | $0.00023 | $0.00609 |
| Haiku 4.5 | $0.00011 | $0.00304 |
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 15d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manim explainer videos
This skill makes short explainer videos in the style of Apple's hardware films: a black background, slow camera moves around a 3D model, parts that lift apart in exploded views, and short headlines with thin callout lines. A video is a Python module built on engine.py, rendered scene by scene and joined into one MP4.
Files
| File | What it is |
|---|---|
assets/engine.py |
The engine: camera, boxes, depth sort, shadows, glow effects, text styles, callouts, bar charts, and the Base scene. Copy it into every video folder. |
assets/template.py |
A working three-scene video (a board, a die, memory stacks, an I/O chip) that uses every technique below. Start every new video from it. |
scripts/preview.py |
Renders still frames of the named states in PREVIEW_STATES, plus sheet.png, which tiles them. Each still takes about 6 seconds. |
scripts/render.sh |
Renders every scene in parallel and joins them. On 18 cores, a 480p15 draft of a 3.5-minute video takes about 35 seconds and the 1080p60 final takes about 4 minutes. |
scripts/review.sh |
Makes one contact sheet per scene and seams.png, which shows the last frame of each scene beside the first frame of the next one. |
Resolve the skill directory before you use these files. ~/.claude/skills/manim-video can be a symlink, and BSD readlink has no -f:
SKILL_LINK=~/.claude/skills/manim-video/SKILL.md
SKILL_TARGET="$(readlink "$SKILL_LINK" 2>/dev/null || echo "$SKILL_LINK")"
SKILL_DIR="$(cd "$(dirname "$SKILL_TARGET")" && pwd -P)"
The scripts pin Python 3.12 and manim 0.21.0 through uv, and they need ffmpeg and ffprobe on the path. Nothing else needs to be installed. Python 3.14 is untested.
Workflow
-
Collect the facts from the source material that the user names. For a PDF, extract the text and find the section in it:
uv run --with pypdf python -c 'import pypdf, sys r = pypdf.PdfReader(sys.argv[1]) for i, p in enumerate(r.pages): print(f"=== PAGE {i+1} ===\n" + (p.extract_text() or ""))' SOURCE.pdf > source.txt
What ships with it
5 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.
- 15d ago First seen · 114 lines · 114 tokens per session scan A 7afc349ec45c
manim-video is a skill published in the GitHub repository surajssd/dotfiles (5 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 3,043 once invoked, about $0.0005 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 2026-10-03.
Other skills, from other repositories
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.