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 vesperchinn/learn-anything-skill --skill learn-anything-skillgit clone --depth 1 https://github.com/vesperchinn/learn-anything-skillWrote 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/vesperchinn/learn-anything-skill/learn-anything-skill)<a href="https://agentmods.dev/skills/vesperchinn/learn-anything-skill/learn-anything-skill"><img src="https://agentmods.dev/badge/skills/vesperchinn/learn-anything-skill/learn-anything-skill/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/vesperchinn/learn-anything-skill/learn-anything-skill"><img src="https://agentmods.dev/badge/skills/vesperchinn/learn-anything-skill/learn-anything-skill.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 | $0.00076 | $0.07869 |
| Opus 5 | $0.00038 | $0.03934 |
| Sonnet 5 | $0.00015 | $0.01574 |
| Haiku 4.5 | $0.00008 | $0.00787 |
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 9d 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 — 761 lines — stays where its author put it; the contents beside it link to each section on GitHub.
learn-anything
Turn any AI agent into a domain learning engineer — scaffold a structured learning repository, generate knowledge maps, run daily learn→practice→output→test cycles, diagnose errors, track progress, and guide a capstone project.
Do Not Use When
Do not use this Skill Pack when the user only wants:
- A one-off factual answer, definition, summary, translation, or quick rewrite
- Professional advice in medical, legal, financial, safety-critical, or other regulated domains
- Guaranteed factual correctness without verification against authoritative sources
- A generic motivational study plan with no file-based learning repository
- Direct publication-ready content unrelated to learning, practice, assessment, or progress tracking
Language and Locale Policy
This Skill Pack supports English and Chinese locales with full separation of interface language and learning material language.
Locale Variables
At intake, capture these variables. They drive every file path and content decision:
| Variable | Description | Example values |
|---|---|---|
{locale} |
Which locale pack to load | en-US, zh-CN |
{interface_language} |
Language for agent-user conversation | English, 中文 |
{learning_language} |
Language for learning materials (may differ) | English, 中文 |
{domain} |
What the user wants to learn | AI Agent, nutrition, 古典音乐 |
{domain_slug} |
Filesystem-safe domain name | ai-agent, nutrition, classical-music |
{user_background} |
Current knowledge level | zero, beginner, intermediate, advanced |
{daily_time} |
Available time per day | 1 hour, 2.5 hours, 45 minutes |
{duration} |
Total learning period in days | 30, 14, 60 |
{learning_goal} |
Why they're learning | exam, work, project, writing, product, research |
{final_artifact} |
What they want to build or produce | a personal research assistant, unsure |
{web_access} |
Whether the agent can verify current sources online | available, unavailable, unknown |
{material_mode} |
Whether user-provided materials define the course scope | true, false |
{material_paths} |
Local files or folders supplied by the user | slides/week1.pptx, docs/*.pdf |
{material_urls} |
Webpage exports or URLs supplied by the user | course-export.html |
{file_read_access} |
Whether the agent can read the supplied files | available, unavailable, unknown |
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.
- 9d ago First seen · 761 lines · 76 tokens per session scan A 0b783a1d5ddf
learn-anything is a skill published in the GitHub repository vesperchinn/learn-anything-skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 7,869 once invoked, about $0.0004 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
improve
Critique an outside idea (a pasted tip, post, transcript or video summary) against what this system already has. Use when the founder pastes something and asks whether to adopt it, or says 'improve', 'should we do this', 'compare this to what we have'. Grounded by scripts/improveground.py in the lessons corpora and…
lineage-skill
Turn courses, books, video, audio, PDFs, slides, transcripts, OCR, notes, and long-form materials into source-grounded learning Skills that teach unseen concepts progressively with reliable terminal ASCII or SVG visuals, ask two end-of-lesson questions together by default, give focused feedback, schedule review, test…
cognitive-compile
Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.
tutorial
Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".
explain
Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…