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 RudraDudhat2509/claude-skills --skill learn-anythinggit clone --depth 1 https://github.com/RudraDudhat2509/claude-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/rudradudhat2509/claude-skills/learn-anything)<a href="https://agentmods.dev/skills/rudradudhat2509/claude-skills/learn-anything"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/learn-anything/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/rudradudhat2509/claude-skills/learn-anything"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/learn-anything.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 | $0.00243 | $0.02196 |
| Opus 5 | $0.00121 | $0.01098 |
| Sonnet 5 | $0.00049 | $0.00439 |
| Haiku 4.5 | $0.00024 | $0.00220 |
Grade A, and why
learn-anything 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn Anything Skill
Turn any resource OR bare concept — YouTube lecture, GitHub repo, research paper, pasted notes, or just a topic name — into a proper learning session. Think of it as your smart friend who knows the stuff cold and is going to teach it to you properly, with examples, problems, and a clear path forward.
Step 1: Identify Input Type
Two distinct modes — figure out which one applies:
Mode A: Resource-based (user gave you something to learn from)
| Source Type | How to handle |
|---|---|
| YouTube URL | Extract transcript if possible via web_fetch on https://www.youtube.com/watch?v=.... If transcript unavailable, ask user to paste key content or timestamps. |
| GitHub repo/README URL | web_fetch the raw README or key files. Focus on the core concept being taught, not boilerplate. |
| arXiv / research paper URL | web_fetch the abstract + sections. For PDFs uploaded directly, read them. Focus on problem statement, method, results, and intuition. |
| Pasted text / notes | Use directly. |
After ingesting, go to Step 2A, then Step 3.
Mode B: Concept-only (user just named a topic — "vlms", "LoRA", "attention", "RLHF")
This is the "I want to learn X" mode with no resource attached. Do NOT just explain the concept — give them a full learning plan plus a taster session.
Go to Step 2B, then Step 3B.
Step 2A: Before Teaching (Resource Mode) — Ask the User Two Things
Always ask these before generating the full session (combine into one short message, don't be annoying about it):
- What's their context? — Are they a beginner, do they know adjacent stuff, any specific angle they care about?
- How deep? — Quick mental model + one example? Or full drill-down with problems?
Keep this super casual. Example:
"Quick q before I dive in — how familiar are you with [topic area]? And do you want the quick-but-solid version or want to really drill into it with problems?"
Step 2B: Concept-Only Mode — Ask and Then Roadmap
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 · 213 lines · 243 tokens per session scan A b43363c49eb0
learn-anything is a skill published in the GitHub repository RudraDudhat2509/claude-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 243 tokens to every session and 2,196 once invoked, about $0.0012 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
gws-classroom
Google Classroom: Manage classes, rosters, and coursework.
recipe-create-classroom-course
Create a Google Classroom course and invite students.
bayesian-reasoning-calibration
Use when making predictions or judgments under uncertainty and need to explicitly update beliefs with new evidence. Invoke when forecasting outcomes, evaluating probabilities, testing hypotheses, calibrating confidence, assessing risks with uncertain data, or avoiding overconfidence bias. Use when user mentions…
abstraction-concrete-examples
Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps. Invoke when…
blackboard-automation
Automate Blackboard tasks via Rube MCP (Composio). Always search tools first for current schemas.
hr-psychometric
Design and interpret workplace psychometric assessments for hiring: cognitive aptitude, work-style, integrity, collaboration, and stress scenarios. Generate rubrics, score sheets, and hiring recommendations for engineers and other roles. Use for psikotest, psychometric, aptitude test, personality assessment…