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/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/kavyabhand/claude-eli5/eli-teach"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-teach.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 | $0.00066 | $0.00548 |
| Opus 5.5 | $0.00026 | $0.00219 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 6mo ago), licensed MIT. It adds 66 tokens to every session and 548 once invoked, about $0.0003 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 2026-08-30.
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…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
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.