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 dbillion/manim-storytelling-skills --skill manim-brilliance-explainergit clone --depth 1 https://github.com/dbillion/manim-storytelling-skillsWrote 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/dbillion/manim-storytelling-skills/manim-brilliance-explainer)<a href="https://agentmods.dev/skills/dbillion/manim-storytelling-skills/manim-brilliance-explainer"><img src="https://agentmods.dev/badge/skills/dbillion/manim-storytelling-skills/manim-brilliance-explainer/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/dbillion/manim-storytelling-skills/manim-brilliance-explainer"><img src="https://agentmods.dev/badge/skills/dbillion/manim-storytelling-skills/manim-brilliance-explainer.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 | $0.00110 | $0.00888 |
| Opus 5.5 | $0.00044 | $0.00355 |
| Sonnet 5.5 | $0.00022 | $0.00178 |
| Haiku 4.5 | $0.00011 | $0.00089 |
Grade A, and why
manim-brilliance-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 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Manim Brilliant Explainer (v3.2)
Purpose
Create math and science animations in the spirit of 3Blue1Brown and Veritasium: clear, elegant, visual-first, narrative-driven, and mathematically precise.
Inputs
- topic
- audience level
- target duration
- desired visual style
- core message
Output
- Core insight statement
- Misconception or hook
- Storyboard with beats
- Manim scene code using the correct technique from the grammar below
- Rendering instructions
- QA checklist
Creative Rules
- One idea per shot.
- Motion must represent meaning.
- Preserve object identity: transform, never fade-swap.
- Use a minimal color palette.
- Use LaTeX for math when appropriate.
- Labels appear near the object they describe.
- Camera movement must have a reason.
- Do not animate more than 3 independent motions at once; stagger the rest.
- Every scene should have a visible aha moment.
- The visual should be understandable even with sound off.
Technique Selection Grammar
Choose the technique by the explanatory job:
- Algebraic manipulation -> TransformMatchingTex (shots/algebra.py)
- Shape morph with same parts -> TransformMatchingShapes
- Same idea in two representations -> TransformFromCopy (shots/linking.py)
- Curve produced by motion -> TracedPath (shots/tracing.py)
- Function plot -> axes.plot, parametric -> plot_parametric_curve
- Naming or grouping -> Brace + label (shots/annotations.py)
- Focus on a term -> SurroundingRectangle (shots/annotations.py)
- Cancellation -> strikethrough Line, never deletion (shots/annotations.py)
- Labels or arrows that follow -> add_updater with become() (shots/followers.py)
- Dynamic graphs that rebuild -> always_redraw + ValueTracker
- Function acting on numbers -> apply_complex_function (shots/complex_maps.py)
- 4 or more elements moving -> lag_ratio cascade (shots/choreography.py)
- Strict sequence in one beat -> Succession (shots/choreography.py)
- One shape becoming another -> Homotopy (shots/deformation.py)
- Limit process -> Transform to a finer version of the same object
- Animated vector fields -> stream.create() (Manim Community)
What ships with it
53 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.
- .gitignore 100 B
- corpus/build_corpus.py 1.5 KB runs code
- corpus/README.md 376 B
- eval/checklist.md 928 B
- eval/rubric.md 587 B
- examples/derivative_tangent.py 2.3 KB runs code
- examples/matrix_transform.py 1013 B runs code
- examples/topics/calculus_trio.py 3.5 KB runs code
- examples/topics/eigenvectors.py 1.7 KB runs code
- examples/topics/electromagnetism.py 2.2 KB runs code
- examples/topics/fourier_epicycles.py 2.3 KB runs code
- examples/topics/neural_network.py 2.3 KB runs code
- prompts/director.md 831 B
- prompts/manim_coder.md 834 B
- prompts/qa_reviewer.md 518 B
- prompts/storyboard_writer.md 489 B
- README.md 3.2 KB
- requirements.txt 6 B
- scripts/download_reference_repos.py 451 B runs code
- scripts/render_all.py 1.7 KB runs code
- shots/__init__.py 476 B runs code
- shots/algebra.py 403 B runs code
- shots/annotations.py 792 B runs code
- shots/choreography.py 197 B runs code
- shots/complex_maps.py 210 B runs code
- shots/deformation.py 293 B runs code
- shots/equation_to_graph.py 872 B runs code
- shots/followers.py 818 B runs code
- shots/hook.py 384 B runs code
- shots/linking.py 569 B runs code
- shots/tracing.py 554 B runs code
- storyboard/example_derivative.json 788 B
- style/__init__.py 111 B runs code
- style/angles.py 936 B runs code
- style/camera.py 1.9 KB runs code
- style/labels.py 228 B runs code
- style/palette.py 303 B runs code
- style/timing.py 546 B runs code
- techniques/__init__.py 65 B runs code
- techniques/annotations_demo.py 1.0 KB runs code
- techniques/choreography.py 1.4 KB runs code
- techniques/complex_mapping.py 733 B runs code
- techniques/homotopy.py 905 B runs code
- techniques/matching_transforms.py 1.0 KB runs code
- techniques/rate_functions_gallery.py 1.5 KB runs code
- techniques/surfaces_3d.py 1.5 KB runs code
- techniques/traced_path.py 1.1 KB runs code
- techniques/transform_from_copy.py 1.1 KB runs code
- techniques/updaters.py 1.8 KB runs code
- templates/__init__.py 19 B runs code
- templates/cinematic_template.py 1.2 KB runs code
- templates/three_minute_explainer.py 900 B runs code
- templates/veritasium_mystery.py 794 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 · 99 lines · 110 tokens per session scan A 1751a6c63f42
manim-brilliance-explainer is a skill published in the GitHub repository dbillion/manim-storytelling-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 888 once invoked, about $0.0004 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 2026-08-31.
manim-brilliance-explainer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| manim-brilliance-explainerdbillion/manim-storytelling-skills | Skill | 3 | 3mo ago | MIT | A | 110 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |