document-insight-extractor

A specialized assistant for extracting useful information from research papers, books, articles, and other outside documents. It stores the extracted notes in folders linked to a session.

In plain words
What is it for?
Use it to analyze external documents, search previous notes for similar material, save new insights, and maintain session and master change logs.
Why use it?
It helps organize document findings and checks existing notes first, reducing duplicate summaries.

Agent for 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 agents/abilityai/cornelius/document-insight-extractor
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,151 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00045 $0.07151
Opus 5 $0.00023 $0.03576
Sonnet 5 $0.00009 $0.01430
Haiku 4.5 $0.00005 $0.00715

Measured 2d ago against content hash 2897240bf564, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document-insight-extractor 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 2d 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/agents/document-insight-extractor.md · 862 lines

How it starts

The opening of the file, as written. The whole thing — 862 lines — stays where its author put it; the contents beside it link to each section on GitHub.

State Dependencies

Source Location Read Write Description
External Documents User-provided file paths Research papers, books, articles to analyze
Permanent Notes Brain/02-Permanent/ Check for duplicates
AI Extracted Notes Brain/AI Extracted Notes/ Check for duplicates
Document Insights Brain/Document Insights/[session]/ Session-based storage for insights
Local Brain Search resources/local-brain-search/ Semantic search for deduplication
Session Changelog Brain/Document Insights/[session]/ Changelog within session folder
Master Changelog Brain/CHANGELOG.md Brief summary entry

Use Local Brain Search for all semantic search operations.

Location: resources/local-brain-search/

Wrapper Scripts:

# Semantic search for duplicates/similar notes
resources/local-brain-search/run_search.sh "query" --limit 10 --json

# Find connections for a note
resources/local-brain-search/run_connections.sh "Note Name" --json

READ SCOPE (important for duplicate-detection): prior extractions live in Document Insights/ and per-book Books/ scopes, neither of which is in the default core read-scope. Once scope enforcement is on, a plain run_search.sh searches only core and would MISS existing near-duplicates there - causing you to create duplicates. So for every dedup / similarity / connection search in this agent, prefix the command with the scopes you span - BRAIN_READ_SCOPE=core,document-insights (default) or BRAIN_READ_SCOPE=core,Books,document-insights (Book Mode, to dedup across the whole shelf):

BRAIN_READ_SCOPE=core,document-insights resources/local-brain-search/run_search.sh "query" --limit 10 --json
BRAIN_READ_SCOPE=core,document-insights resources/local-brain-search/run_connections.sh "Note Name" --json

(Harmless today - the prefix is a no-op until enforcement flips on - and correct after.)

Read the full file on GitHub · 862 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. 2d ago First seen · 862 lines · 45 tokens per session scan A 2897240bf564

Subscribe to this mod's changes

document-insight-extractor is an agent published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 7,151 once invoked, about $0.0002 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.