eli-deeper

eli-deeper is a skill for Claude Code, Codex from kavyabhand/claude-eli5. It costs 63 tokens per session (400 once invoked), scanned B, original, MIT.

A mode that re-explains the most recently discussed concept at the next level of technical detail, from beginner explanations toward expert-level language.

In plain words
What is it for?
Use it after an introductory explanation when you want one step more detail, more technical vocabulary, or a deeper treatment of the same subject.
Why use it?
It lets you deepen understanding gradually instead of jumping from a simple explanation to unfamiliar technical detail. It also keeps the explanation focused on the concept already being discussed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Install

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.

agentmods
npx agentmods add skills/kavyabhand/claude-eli5/eli-deeper
Any agent
npx skills add kavyabhand/claude-eli5 --skill eli-deeper
Clone the repo
git clone --depth 1 https://github.com/kavyabhand/claude-eli5

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for eli-deeper

README.md
[![agentmods](https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-deeper.svg)](https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-deeper)
Your own site
<a href="https://agentmods.dev/skills/kavyabhand/claude-eli5/eli-deeper"><img src="https://agentmods.dev/badge/skills/kavyabhand/claude-eli5/eli-deeper.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 400 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00400
Opus 5 $0.00032 $0.00200
Sonnet 5 $0.00013 $0.00080
Haiku 4.5 $0.00006 $0.00040

Measured 6d ago against content hash 5d24e7257de0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

eli-deeper 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-state.json 2>/dev/null || echo "none"
skills/eli-deeper/SKILL.md · 48 lines

What it actually says

ELI5 Deeper — Step Up One Level

Move one step more technical on the level ladder, then re-explain the last concept at the new level.

The Level Ladder

eli5 (1) → eli-kid (2) → eli-teen (3) → eli-adult (4) → eli-expert (5)
                                                               ↑ most technical

Steps

  1. Check current level:

    cat .claude/eli5-state.json 2>/dev/null || echo "none"
    
  2. Determine next level up:

    • eli5 → eli-kid
    • eli-kid → eli-teen
    • eli-teen → eli-adult
    • eli-adult → eli-expert (ask for their field if not saved in .claude/eli5-expert-field)
    • eli-expert → already at max; tell the user in one sentence
  3. Update state:

    printf '{"level":"[new-level]","label":"[new-label]"}' > .claude/eli5-state.json
    
  4. Acknowledge the level change in one sentence at the NEW level's style.

  5. Re-explain the most recent concept at the new level — don't just announce the switch. If no concept was recently explained, just confirm the new level is active.

Important

Apply the new level's rules immediately. Read the core rules at: ~/.claude/skills/eli5-mode/references/core-rules.md

Changes

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.

  1. 6d ago First seen · 48 lines · 63 tokens per session scan B 5d24e7257de0

Subscribe to this mod's changes

eli-deeper is a skill published in the GitHub repository kavyabhand/claude-eli5 (21 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 400 once invoked, about $0.0003 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.

Related

Other skills, from other repositories