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 agentmods add skills/kavyabhand/claude-eli5/eli-prereqsnpx skills add kavyabhand/claude-eli5 --skill eli-prereqsgit 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-prereqs)<a href="https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-prereqs"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-prereqs.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 | $0.00084 | $0.00549 |
| Opus 5 | $0.00042 | $0.00275 |
| Sonnet 5 | $0.00017 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade B, and why
eli-prereqs scanned grade B with 1 finding 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/eli5-concepts.json 2>/dev/null | head -50 What it actually says
ELI-PREREQS — Learning Path
Given a topic, map the path from zero to understanding — so you know where to start, not just where to end up.
Steps
1. Check what the user already knows (optional)
If the user mentioned their background in this session, use it. Otherwise, ask once: "What's your starting point? (e.g., beginner, some coding, experienced in [field])" If they want to skip this: proceed with eli-adult level assumptions.
2. Check past concepts (cross-session awareness)
cat .claude/eli5-concepts.json 2>/dev/null | head -50
If a concept appears there, it's already been covered — skip it or mark as "(you've seen this)".
3. Produce the learning path
Format:
## To understand [topic], you first need:
1. **[Prerequisite A]** — [one plain-language sentence. How long: ~X hours/days]
2. **[Prerequisite B]** — [one plain-language sentence. How long: ~X hours/days]
3. **[Prerequisite C]** — [one plain-language sentence. How long: ~X hours/days]
## Then: [Topic itself]
[One-sentence plain-language summary of what it is, once you have the above]
## After this, you'll be ready for:
- [Next concept 1]
- [Next concept 2]
## Start here →
[The single best first step — a command, a tutorial, a book, or a concept to ask about next]
Rules
- Keep prerequisites concrete — no "understand programming fundamentals" vagueness
- Time estimates should be honest, not optimistic
- Flag prerequisites that are themselves complex: "(this one takes a few days — don't rush it)"
- Maximum 5 prerequisites — if there are more, chain them: do A, then B, then ask again
- "Start here →" must be actionable: something specific to read, watch, or ask about
- Match the active eli5 level (or eli-adult if not active)
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.
- 6d ago First seen · 56 lines · 84 tokens per session scan B 4d973e5a76b5
eli-prereqs is a skill published in the GitHub repository kavyabhand/claude-eli5 (21 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 549 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…