digest-this

digest-this is a skill for Claude Code, Codex from 8ix/neurodiverse-claude-skills. It costs 96 tokens per session (1,598 once invoked), scanned A, original, MIT.

A skill that turns long or difficult content—such as documents, PDFs, transcripts, and messages—into a short, structured summary. It asks what the reader needs before summarising.

In plain words
What is it for?
It helps someone quickly understand the main points of dense content through brief, scannable output rather than reading everything in full.
Why use it?
It prevents a summary from becoming almost as long and hard to read as the original material.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps someone quickly understand the main points of dense content through brief, scannable output rather than reading everything in full.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/8ix/neurodiverse-claude-skills/digest-this
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.

Any agent
npx skills add 8ix/neurodiverse-claude-skills --skill digest-this
Clone the repo
git clone --depth 1 https://github.com/8ix/neurodiverse-claude-skills

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 digest-this

README.md
[![agentmods](https://agentmods.dev/badge/skills/8ix/neurodiverse-claude-skills/digest-this/github.svg)](https://agentmods.dev/skills/8ix/neurodiverse-claude-skills/digest-this)
Your own site
<a href="https://agentmods.dev/skills/8ix/neurodiverse-claude-skills/digest-this"><img src="https://agentmods.dev/badge/skills/8ix/neurodiverse-claude-skills/digest-this/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for digest-this

Your own site · 80×15
<a href="https://agentmods.dev/skills/8ix/neurodiverse-claude-skills/digest-this"><img src="https://agentmods.dev/badge/skills/8ix/neurodiverse-claude-skills/digest-this.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,598 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00096 $0.01598
Opus 5 $0.00048 $0.00799
Sonnet 5 $0.00019 $0.00320
Haiku 4.5 $0.00010 $0.00160

Measured 12d ago against content hash 5a2f868b61fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

digest-this 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 12d 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.

skills/digest-this/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Digest This

A skill that sits between you and long or complex content, making it accessible without losing what matters.

This skill does one thing: takes something long, dense, or hard to read and turns it into something short, clear, and scannable. The output is always brief regardless of how long the input is. A ten page document and a long email get the same treatment — a short, structured summary the user can actually absorb.


What Makes This Different From a Standard Summary

Claude's default behaviour is to produce summaries proportional to the input — long document, long summary. This skill enforces the opposite. The output is always short. Always structured. Never a wall of text.

It also asks one question before acting, so the output is shaped around what the user actually needs rather than what Claude assumes they need. And it produces the same reliable format every time, regardless of how the user asks.


When to Apply

Apply automatically when:

  • The user pastes in a long block of text, document, transcript, or message
  • The content is clearly longer than the user needs to read in full
  • The user says things like "what does this say", "can you summarise this", "digest this", "what's this about", "too long didn't read", or "tldr"

Apply on manual trigger with /digest-this

Do not apply when:

  • The content is already short and clear
  • The user is asking a specific question about the content rather than wanting a summary
  • The user wants to discuss or analyse the content in depth rather than get a quick digest

Core Principles

Always short The output must be short regardless of input length. This is non-negotiable. A one page document and a fifty page report both get a short digest. If the user needs more depth they can ask.

Scannable over readable Structure matters more than prose. Use headings, short bullets, and white space. A user should be able to get the key information in under sixty seconds without reading every word.

Read the full file on GitHub · 185 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. 12d ago First seen · 185 lines · 96 tokens per session scan A 5a2f868b61fd

Subscribe to this mod's changes

digest-this is a skill published in the GitHub repository 8ix/neurodiverse-claude-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 1,598 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

chatdoc-studio-api

ChatDOC Studio API usage guide - complete documentation and examples for PDF parsing, chat applications, agent applications, content retrieval, and data extraction APIs.

chatdoc-com/chatdoc-studio-skills · 34 tokens

ChatDOC Studio--KnowledgeMate

Create and operate ChatDOC Studio knowledge bases through pdrouter using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base…

PaodingAI/skills · 92 tokens

PDFlux-PDF2Markdown

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other elements in one step; generates up to 8 levels of headings; and outputs Markdown organized in reading order. Useful for field extraction, comparison and…

PaodingAI/skills · 78 tokens

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

liteparse

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities…

K-Dense-AI/scientific-agent-skills · 86 tokens

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens