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-expertgit 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-expert)<a href="https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-expert"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-expert.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 | $0.00095 | $0.00522 |
| Opus 5 | $0.00048 | $0.00261 |
| Sonnet 5 | $0.00019 | $0.00104 |
| Haiku 4.5 | $0.00010 | $0.00052 |
Grade B, and why
eli-expert scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/eli5-expert-field 2>/dev/null || echo "" What it actually says
ELI5 Mode — Expert Bridge
Active every response until deactivated. Per-turn reinforcement is handled by the hook.
This level: Expert in an adjacent field
Step 1 — identify their domain:
cat .claude/eli5-expert-field 2>/dev/null || echo ""
If saved: use it, don't ask again.
If empty: ask "What's your background? I'll use your domain's vocabulary."
Once told: mkdir -p .claude && printf '[field]' > .claude/eli5-expert-field
Step 2 — bridge, don't teach:
- Use their domain's jargon freely as the bridge.
- Replace the target domain's jargon with structural equivalents from their world.
- Make the connection explicit: "In your world this is like X. Here it works the same way."
Example bridges: TCP/IP to a doctor → patient handoffs. Git to a lawyer → versioned contract drafts. Databases to a chef → recipe cards + pantry inventory.
Analogy resources
~/.claude/skills/eli5-mode/references/custom-analogies.md~/.claude/skills/eli5-mode/references/analogy-bank.md
Full enforcement rules: ~/.claude/skills/eli5-mode/references/core-rules.md
On activation
If field known: confirm in one sentence using their vocabulary. If field unknown: ask for it before answering anything.
State
mkdir -p "${CLAUDE_CONFIG_DIR:-$HOME/.claude}" .claude && \
printf '{"level":"eli-expert","label":"expert bridge","session":"%s"}' "${CLAUDE_SESSION_ID:-}" \
> "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/.eli5-active.json" && \
printf '{"level":"eli-expert","label":"expert bridge"}' > .claude/eli5-state.json
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 · 48 lines · 95 tokens per session scan B 73f046a21fec
eli-expert is a skill published in the GitHub repository kavyabhand/claude-eli5 (21 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 522 once invoked, about $0.0005 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
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.