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 redhuntlabs/wizard --skill learning-something-newgit clone --depth 1 https://github.com/redhuntlabs/wizardWrote 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/redhuntlabs/wizard/learning-something-new)<a href="https://agentmods.dev/skills/redhuntlabs/wizard/learning-something-new"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/learning-something-new/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/redhuntlabs/wizard/learning-something-new"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/learning-something-new.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 | $0.00028 | $0.01005 |
| Opus 5.5 | $0.00011 | $0.00402 |
| Sonnet 5.5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
learning-something-new 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Something New
What this does
Turns "I want to learn X" into a structured plan: a concrete first project, a small number of high-signal sources, and a checkpoint to detect when you've stalled.
When to use
- Picking up a new tool, language, framework, or domain
- Onboarding to a new role or team
- Catching up on a topic for an upcoming conversation
- Hobby learning (instrument, sport, craft)
What you bring (Inputs)
- The thing you want to learn
- Why you want to learn it (the use case — concrete, not "to be smarter")
- Time available per week
- Your existing knowledge level (none / some / experienced in adjacent)
What you get (Output)
A learning plan: first useful project, source list (max 5), checkpoints with a rescue plan if stalled.
How it works (Steps)
This is a workflow.
Stages
Stage 1: Define the first useful output
What's the smallest thing you could make / do / decide that would prove you've learned the basics? This is your first project.
Examples: "Deploy a hello-world service in this framework," "Hold a 5-minute conversation in this language," "Diagnose a basic bug in this codebase," "Bake a loaf of sourdough."
Stage 2: Pick 2-3 starter sources
Not 12. Two to three high-quality sources for the basics, picked from a known canonical reference (official docs, top-recommended book, top course). Resist the urge to bookmark 20 things.
Stage 3: Schedule the first sprint
When are you doing this in the next 7 days? Block calendar time. Without a block, the plan is wishful thinking.
Stage 4: Set checkpoints
After 1 week, you should have completed the first useful output. After 4 weeks, you should be able to do a slightly harder version.
If you've not hit checkpoint 1, run the rescue plan.
Stage 5: Rescue plan (when stalled)
Common causes of stall (with fixes):
- Too many sources: cut to 1
- Too big a first project: shrink it (hello-world, then a step up)
- No application: the gap from "learning" to "doing" is widening; force a doing-mode session
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.
- 1mo ago First seen · 111 lines · 28 tokens per session scan A cbae09a6d47a
learning-something-new is a skill published in the GitHub repository redhuntlabs/wizard (10 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,005 once invoked, about $0.0001 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.
Other skills, from other repositories
paper-checking
A Windows application for finding copied text in documents. It compares files with a reference collection or compares documents in the same batch with one another.
teach
Uses the Feynman technique - explain simply to detect where knowledge gaps exist. Now with mathematical depth metrics, gap severity calculus, teaching effectiveness, and verification gates.
wisdom-decoder
A guided explanation skill for ideas from Buddhism, philosophy, and psychology. It presents a chosen topic in everyday language and connects it to practical actions, sources, and perspectives from other fields.
book-recommender
A Chinese-language book recommendation and analysis skill that evaluates what books are about, whether they are worth reading, and how to read them.
daily-knowledge
A daily knowledge prompt that gives one concise, non-repeated fact from a rotating range of subjects, such as science, history, psychology, or technology. It is designed for a short read and includes an explanation, a takeaway, a related fact, and wider context.
feynman-write
A research-and-writing workflow based on the Feynman method, where the AI gathers source material and the author decides the article's focus, then explains the ideas through questioning. The final text keeps the author's own examples and voice while adding technical precision.