deep-reading-analyst-skill CLAUDE.md

deep-reading-analyst-skill CLAUDE.md is an instructions file for Claude Code from ginobefun/deep-reading-analyst-skill. It costs 2,231 tokens per session, scanned A, original, MIT.

A guide for a Claude AI skill that provides structured analysis of articles, research papers, and other long-form writing. It organizes analysis into levels ranging from quick summaries to comparisons across multiple sources.

In plain words
What is it for?
Use it to analyze writing with methods such as 5W2H, which asks who, what, when, where, why, how, and how much; evaluate reasoning; examine risks; and compare sources.
Why use it?
It helps turn passive reading into a repeatable examination of structure, arguments, assumptions, risks, and connections between ideas.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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 instructions/ginobefun/deep-reading-analyst-skill/claude-md
Clone the repo
git clone --depth 1 https://github.com/ginobefun/deep-reading-analyst-skill

Made for: Claude Code.

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 deep-reading-analyst-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ginobefun/deep-reading-analyst-skill/claude-md.svg)](https://agentmods.dev/instructions/ginobefun/deep-reading-analyst-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ginobefun/deep-reading-analyst-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ginobefun/deep-reading-analyst-skill/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,231 This file is loaded in full into every session.
When invoked 2,231 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02231 $0.02231
Opus 5 $0.01115 $0.01115
Sonnet 5 $0.00446 $0.00446
Haiku 4.5 $0.00223 $0.00223

Measured 6d ago against content hash 77fc21867ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deep-reading-analyst-skill CLAUDE.md 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 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.

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.

CLAUDE.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Deep Reading Analyst is a Claude AI skill (.skill file) that provides systematic framework for deep analysis of articles, papers, and long-form content using multiple thinking models. It transforms surface-level reading into deep learning through structured workflows.

Core Purpose

This skill guides users through a 5-step analysis process using 10+ proven thinking frameworks:

Quick Analysis (15min):

  • SCQA Framework (structure thinking)
  • 5W2H Analysis (completeness check)

Standard Analysis (30min):

  • Critical Thinking (argument evaluation, logical fallacy detection)
  • Inversion Thinking (risk and failure mode analysis)

Deep Analysis (60min):

  • Mental Models (multi-discipline perspectives: physics, biology, psychology, economics)
  • First Principles (assumption stripping, essence extraction)
  • Systems Thinking (causal loops, knowledge connections)
  • Six Thinking Hats (multi-perspective evaluation)

Research Level (120min+):

  • Cross-Source Comparison (multi-article synthesis)

Repository Structure

Source Files

  • src/deep-reading-analyst/ - Source files for the skill (tracked in Git)
    • SKILL.md - Main workflow and decision tree
    • references/ - Detailed framework documentation (10+ frameworks)
      • scqa_framework.md - McKinsey structure thinking (NEW!)
      • 5w2h_analysis.md - Completeness check with 7 questions (NEW!)
      • critical_thinking.md - Argument analysis framework
      • inversion_thinking.md - Charlie Munger's risk analysis (NEW!)
      • mental_models.md - 30+ models from multiple disciplines (NEW!)
      • first_principles.md - Elon Musk's assumption identification
      • systems_thinking.md - Relationship mapping and causal loops
      • six_hats.md - Edward de Bono's multi-perspective protocol
      • output_templates.md - 8 different output formats
      • comparison_matrix.md - Multi-source comparison methodology

Read the full file on GitHub · 285 lines

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 · 285 lines · 2,231 tokens per session scan A 77fc21867ff6

Subscribe to this mod's changes

deep-reading-analyst-skill CLAUDE.md is an instructions file published in the GitHub repository ginobefun/deep-reading-analyst-skill (347 stars, last pushed 10mo ago), licensed MIT. It adds 2,231 tokens to every session, about $0.0112 per session on Opus 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.