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 HarleyCoops/KimiK3Manim --skill kimi3manimgit clone --depth 1 https://github.com/HarleyCoops/KimiK3ManimWrote 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/harleycoops/kimik3manim/kimi3manim)<a href="https://agentmods.dev/skills/harleycoops/kimik3manim/kimi3manim"><img src="https://agentmods.dev/badge/skills/harleycoops/kimik3manim/kimi3manim/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/harleycoops/kimik3manim/kimi3manim"><img src="https://agentmods.dev/badge/skills/harleycoops/kimik3manim/kimi3manim.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 | $0.00015 | $0.01096 |
| Opus 5 | $0.00008 | $0.00548 |
| Sonnet 5 | $0.00003 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
kimi3manim 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 12d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kimi3Manim: concept to rendered film
Drive the Kimi3Manim six-agent pipeline (Concept Scout, Mathematical Enricher, Visual Designer, Narrative Composer, Manim Coder, vision Render Critic under a deterministic supervisor) to turn any math or physics concept into a rendered 1080p Manim film.
When to Use
- The user asks to animate, visualize, or make a video/film of a mathematical or physical concept, at any level from middle-school geometry to graduate physics.
- The user wants to resume or debug a failed animation run.
- The user wants an existing Manim scene re-rendered.
Quick Reference
| Task | Command (run in the repo directory) |
|---|---|
| Full pipeline, concept to mp4 | uv run python -m k3_agents.supervisor "<concept>" --quality qh |
| Resume failed run at Stage 5 | uv run python resume_pipeline.py [run_dir] |
| Re-render a scene, no model calls | uv run manim -qh <file.py> <SceneClass> |
| One-time subscription login | uv run kimi login |
| Install deps | uv sync |
Quality flags: ql 480p (smoke test), qm 720p, qh 1080p, qk 4K.
--max-repairs N bounds coder/critic repair rounds (default 3).
Procedure
- Locate the repo (config
kimi3manim.repo, default~/KimiK3Manim). Missing?git clone https://github.com/HarleyCoops/KimiK3Manim.git, thenuv syncinside it. System deps: ffmpeg, texlive, texlive-latex-extra, dvisvgm. - Verify auth: either the user ran
uv run kimi loginonce (Kimi Code OAuth subscription - the default), orMOONSHOT_API_KEYis set in.env(also enables the vision critic stage). - Warn the user that a full run takes minutes and spends Kimi quota (six kimi-k3 calls at max reasoning plus rendering); never launch runs in parallel.
- Phrase the concept the way the intended audience would ask it - the Scout calibrates prerequisite depth from the phrasing. "why the Pythagorean theorem is true" is as valid as "the double cover of SO(3)".
- Run the supervisor command. The built-in preflight aborts with exact instructions if the environment is broken - relay its message verbatim and fix the environment; do not retry the pipeline.
- Outputs land in
output/k3_runs/<slug>/: numbered JSON artifacts (01 knowledge graph ... 06 critique), generated scenes inscenes/, per-attemptrender_attemptN.log, and the mp4 undermedia/. Deliver the mp4.[[as_document]]
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.
- 12d ago First seen · 96 lines · 15 tokens per session scan A ae94eb057d13
kimi3manim is a skill published in the GitHub repository HarleyCoops/KimiK3Manim (143 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,096 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
html-ppt-zhangzara-monochrome
A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-illustration-image2
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
paper2video
Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video by fully delegating slide authoring to the installed ppt-master skill and fully delegating rendering, subtitles, timeline assembly, and strict media QA to the installed pptx2video skill and its public CLI. Resolves one…
figure-composer
Compose one publication-grade multi-panel figure. Start from a one-line claim plus immutable data Artifact Version references, or inspect an existing figure and draft its outline directly. Plan a 12-column panel outline, delegate one worker per panel, compose and inspect the result, then run at most three adversarial…