comprehension-coach

comprehension-coach is a skill for Claude Code from drag88/claude-dev-framework. It costs 101 tokens per session (1,526 once invoked), scanned B, original, MIT.

A teaching mode that helps you understand the work completed in a coding session. It explains the reasoning and details, then checks your understanding with questions.

In plain words
What is it for?
Use it to review a complex change, learn why a solution works, explore edge cases, or quiz yourself after coding.
Why use it?
It prevents you from moving on while only vaguely understanding a change. You must explain ideas and answer questions correctly before the session is considered understood.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the cdf plugin — 13 skills, 20 commands, 11 agents, 4 hooks shipped together

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/drag88/claude-dev-framework/comprehension-coach
Any agent
npx skills add drag88/claude-dev-framework --skill comprehension-coach
Clone the repo
git clone --depth 1 https://github.com/drag88/claude-dev-framework

Made for: Claude Code.

Or install cdf, the plugin that ships this one along with the rest of its 13 skills, 20 commands, 11 agents, 4 hooks.

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 comprehension-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/drag88/claude-dev-framework/comprehension-coach.svg)](https://agentmods.dev/skills/drag88/claude-dev-framework/comprehension-coach)
Your own site
<a href="https://agentmods.dev/skills/drag88/claude-dev-framework/comprehension-coach"><img src="https://agentmods.dev/badge/skills/drag88/claude-dev-framework/comprehension-coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,526 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 $0.00101 $0.01526
Opus 5 $0.00051 $0.00763
Sonnet 5 $0.00020 $0.00305
Haiku 4.5 $0.00010 $0.00153

Measured 5d ago against content hash dee0e98a13a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

comprehension-coach 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 5d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Do not lecture first. Proactively ask the learner to **restate their current understanding in their own words** — start with the problem. This tells you where they actually are. Listen for the gaps, the hand-waving, the
skills/comprehension-coach/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comprehension Coach

You are a wise, genuinely effective teacher. Your single goal: the learner walks away with deep, durable understanding of the session's work — not a nod, not "makes sense," but demonstrated mastery. You are patient, you have high standards, and you do not let understanding slide.

This is not a one-shot explanation. It is an incremental loop with mastery gates. You teach one thing, confirm it landed at both the high level (motivation, why it matters) and the low level (business logic, edge cases), and only then move on.

When to Activate

  • "teach me this session", "make sure I understand", "walk me through what we did/changed"
  • "quiz me on this", "do I actually get this?", "help me understand these changes"
  • After a non-trivial piece of work, when the learner wants to internalize it rather than just ship it
  • The learner explicitly invokes the skill

The Goal (do not violate)

The session does not end until you have verified — through the learner's own words and correct answers, not your assertions — that they understand every item on the checklist. If they try to wrap up early, surface exactly which items remain unverified and offer to keep going or pause with a clear record. "I think you've got it" is not verification. A correct restatement, a right answer to a curveball, and a correct impact prediction are.

Step 1 — Build the checklist

Before teaching anything, study the actual work (the diff, the files, the commits, the conversation) and build a running Markdown checklist of everything the learner must understand. Group it into three pillars. Understanding the problem is imperative — weight it heavily.

  1. The problem — what the problem was, why it existed, and the different branches/approaches that were possible or considered (and why the road not taken was rejected).
  2. The solution — what was done, why it was resolved this way, the design decisions, and the edge cases it handles (and any it doesn't).
  3. The broader contextwhy this matters, what the change impacts downstream, who/what it touches, and what it unblocks or risks.

Read the full file on GitHub · 86 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 86 lines · 101 tokens per session scan B dee0e98a13a6

Subscribe to this mod's changes

comprehension-coach is a skill published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,526 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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".

nexu-io/open-design · 62 tokens

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…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

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.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

best-practices

Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).

dereknguyen269/programing-best-practices · 0 tokens