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-dsa-single-pathgit 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-dsa-single-path)<a href="https://agentmods.dev/skills/dbillion/manim-storytelling-skills/manim-dsa-single-path"><img src="https://agentmods.dev/badge/skills/dbillion/manim-storytelling-skills/manim-dsa-single-path/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-dsa-single-path"><img src="https://agentmods.dev/badge/skills/dbillion/manim-storytelling-skills/manim-dsa-single-path.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 | $0.00131 | $0.01233 |
| Opus 5 | $0.00066 | $0.00616 |
| Sonnet 5 | $0.00026 | $0.00247 |
| Haiku 4.5 | $0.00013 | $0.00123 |
Grade A, and why
manim-dsa-single-path 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manim DSA Single-Path Walkthrough
Relationship to the other two skills
Read manim-explainer-animations/SKILL.md first (owns the mobject/animation API surface), then
manim-dsa-storytelling/SKILL.md for the full 3D-solid vocabulary table and the code-duality rules
(real source in a Code mobject, synced SurroundingRectangle highlight, add_fixed_in_frame_mobjects
for HUD text) -- this file only overrides the narrative shape, since a single-path video has one
walkthrough instead of a brute-vs-optimized comparison. Reuse the solid vocabulary and code-duality
rules verbatim; do not reinvent them here.
When to use this instead of manim-dsa-storytelling
Use this skill when the target is one of:
- A sort, traversal, or search with one standard approach (bubble/merge/quick/heap sort, BFS, DFS, Dijkstra, topological sort, MST algorithms)
- A tree or graph operation (max depth, LCA, diameter, cycle detection, bipartite check)
- A single-pass or single-table DP (fibonacci, climb stairs, knapsack, LCS) where there isn't a genuinely worse baseline worth animating
- A data structure's core mechanics (linked list reversal, stack/queue built from arrays, trie, segment tree, union-find)
- A bit trick or simple math routine (XOR tricks, sieve of Eratosthenes, GCD, fast exponentiation)
If a genuine brute-force baseline exists AND the complexity gap is real and instructive, use
manim-dsa-storytelling instead -- don't force a two-path video into this one-path skill just
because it's less work, and don't force a single-path video into a fake "brute force" frame just
to reuse the comparison skill.
The narrative shape (4 acts, ~30-50s total)
- Cold open -- the structure, spatially. Build the data structure/space with the solid from the vocabulary table (same table as manim-dsa-storytelling) before any code appears.
- The walkthrough -- code and motion together. Bring in the real source in a
Codemobject (real, verbatim) with a synced highlight tracking the active line, while a particle/marker moves through the 3D structure performing the algorithm. This is the largest act. For anything beyond ~8-10 elements/nodes/steps, subsample or useChangeSpeed/run_time compression. - The key property. A short beat naming why this approach works -- loop invariant, structural guarantee, base case. Give it a real breath (Write + wait).
- Payoff -- the result, held. Show the final state clearly (sorted array, shortest path traced in the accent color, returned value, built structure). Optionally caption the complexity as a fixed-in-frame label.
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 · 81 lines · 131 tokens per session scan A 9959951e69b9
manim-dsa-single-path is a skill published in the GitHub repository dbillion/manim-storytelling-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 1,233 once invoked, about $0.0007 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.