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 agentmods add skills/tokenbender/agent-guides/manim-math-explainernpx skills add tokenbender/agent-guides --skill manim-math-explainergit clone --depth 1 https://github.com/tokenbender/agent-guidesWhat 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 | $0.00124 | $0.00813 |
| Opus 5 | $0.00062 | $0.00407 |
| Sonnet 5 | $0.00025 | $0.00163 |
| Haiku 4.5 | $0.00012 | $0.00081 |
Grade A, and why
manim-math-explainer 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 2d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
- Default to Manim Community Edition.
- Build scenes that explain one idea at a time.
- Prefer official Manim APIs and example-gallery patterns over low-level point editing.
- Optimize for quick iteration first, polish second.
Read First
rules/core-workflow.mdrules/visual-style.mdrules/proof-layouts.mdrules/text-and-math.mdrules/dynamics-and-graphing.md
When a request is mainly about aesthetics, composition, pacing, or visual tone,
prioritize rules/visual-style.md and keep the rest secondary.
Default Operating Rules
- Confirm the stack before writing code.
If imports or commands suggest
manimglormanimlib, stop and switch mental models. - Start with one compact scene in one file.
- Build in this order: create, position, style, animate.
- Prefer
Create,Write,FadeIn,FadeOut,Transform,ReplacementTransform,TransformMatchingTex, and.animate. - Use
Textfor prose,MathTexfor formulas, andTexonly when mixing prose with LaTeX intentionally. - Use
ValueTrackerwithalways_redraw(...)or simple updaters for dynamic geometry. - Keep color semantics stable across the whole scene.
- Use camera movement only when it adds meaning.
Visual Defaults
- Editorial, proof-first composition
- One focal point per beat
- Stable layout and restrained camera motion
- Limited semantic palette instead of decorative multicolor styling
- Smooth, identity-preserving transforms over flashy effects
- Clean negative space and readable frame density
Render Loop
manim -pql scene.py SceneName
manim -sql scene.py SceneName
manim -pqm scene.py SceneName
manim -qh scene.py SceneName
-pql: fast development loop-sql: save last frame only-pqm: medium-quality check-qh: final render
Preferred Toolbox
- Layout:
VGroup,Group,arrange,arrange_in_grid,next_to,align_to,to_edge,to_corner - Emphasis:
SurroundingRectangle,Brace,Arrow,Indicate,Circumscribe - Equation work:
MathTex,TransformMatchingTex,substrings_to_isolate,index_labels - Dynamic scenes:
ValueTracker,always_redraw,add_updater,TracedPath - Plotting:
Axes,NumberPlane,axes.plot,axes.get_graph_label,axes.i2gp
What ships with it
7 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.
- 2d ago First seen · 89 lines · 124 tokens per session scan A 88e283b8b570
manim-math-explainer is a skill published in the GitHub repository tokenbender/agent-guides (368 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 124 tokens to every session and 813 once invoked, about $0.0006 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
paper-slides
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
paper-talk
End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline"…
clinical-q-and-a
快速回答普通教育性医学问题与常见误区。默认用一份国内现行权威指南/共识完成轻量核验并立即作答;不用于个体诊疗、处方剂量、精确推荐定位、药品高风险事实、医保监管或跨版本比较。.
edu-chem-reaction
把一个化学反应做成自包含的微观 3D 交互演示网页:左/上为 Three.js 可交互分子动画 (拖滑块看断键·成键·原子重组,分步高亮),右为 KaTeX 反应方程 + 分步讲解 + 原子守恒计数 + 可选能量-反应进程曲线。支持三入口——给定文字反应/方程、随机出题、上传图片识别后演示。 覆盖燃烧、化合/分解/置换/复分解、氧化还原(电子转移可视化)、有机机理(酯化等含催化剂·过渡态)。 统一由 sympy 精确驱动:自动配平方程、校验原子守恒与原子映射、推导键的断/成,答案与几何同源一致。 内置两套引擎并自动选择:morph(原子变形,展示原子守恒)与 mechanism(机理关键帧,展示催化/过渡态)。 混合几何:默认自建…
evomath-tao
Use this skill whenever the user submits a non-trivial mathematical claim that needs a rigorous proof or audit. Trigger on IMO/Putnam/USAMO/Olympiad-style problems, ML/AI theoretical statements, research conjectures, suspected-false claims, multi-step proofs the user already failed on, proof drafts with possible…
present-paper
Academic presentation preparation — paper-driven (journal club, grand rounds, seminar) and lecture/teaching decks (course material, workshop slides, conference talks). Analyzes source material, finds supporting references, drafts audience-adapted speaker scripts, generates or augments PPTX with speaker notes, and…