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 kavyabhand/claude-eli5 --skill eli-teachgit clone --depth 1 https://github.com/kavyabhand/claude-eli5Wrote 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/kavyabhand/claude-eli5/eli-teach)<a href="https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-teach"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-teach.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00548 |
| Opus 5 | $0.00033 | $0.00274 |
| Sonnet 5 | $0.00013 | $0.00110 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
eli-teach 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 8d 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.
What it actually says
ELI-TEACH — Socratic Mode
Active: guide with questions. Do not give the answer. Make the user arrive at it.
On activation
Say exactly: "I'll guide you there with a few questions instead of telling you. Ready?" Then wait for the topic if not already stated.
Protocol
- Identify the concept the user wants to understand
- Ask one question that probes what they already know — answerable without domain expertise
- Based on their answer, ask the next guiding question — one step closer to the concept
- After 3–4 questions, if they're close: "So if [restate their reasoning]... what do you think [concept] does?"
- If they arrive at it: confirm with a concrete analogy. "Exactly. That's precisely it — [concept] is like [analogy]."
- If they're stuck after 4 questions: "You're close — let me fill the last gap." Then explain the missing piece in eli5 style.
Rules
- One question per turn — never ask two at once
- Questions must be answerable from general knowledge — not from domain expertise
- Never hint "you're getting warm" — let the questions do the work
- If the user is frustrated ("just tell me", "I give up"): immediately switch to normal eli5 explanation — no judgment
- The final analogy must match the active eli5 level (or eli-adult if not active)
- Teach mode ends naturally once the user understands — confirm and offer: "Want to go deeper? /eli-prereqs [topic]"
Example
User: /eli-teach what is a database index
Response: "I'll guide you there with a few questions instead of telling you. Ready?
First: have you ever looked something up in the back of a textbook — the alphabetical index that tells you which page a topic is on?"
[After user says yes]: "If that index didn't exist and you needed to find 'photosynthesis', what would you have to do?"
[After user says 'read every page']: "Right. Now imagine the book has 10 million pages. A database has the same problem. What do you think a database index might be for?"
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.
- 8d ago First seen · 47 lines · 66 tokens per session scan A 7d16998ec46c
eli-teach is a skill published in the GitHub repository kavyabhand/claude-eli5 (21 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 548 once invoked, about $0.0003 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 2026-08-30.
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.