doc-reader

A document-analysis agent that reads enterprise documents and extracts requirements, technical details, summaries, or comparisons. It checks whether information is current, relevant, and stated as fact or interpretation.

In plain words
What is it for?
Use it to find or read documents, extract functional and security requirements, summarize decisions and caveats, or compare multiple documents.
Why use it?
It reduces the need to read long business and technical documents manually and helps separate reliable statements from assumptions or outdated material.

Agent

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/gleanwork/cursor-plugins/doc-reader
Clone the repo
git clone --depth 1 https://github.com/gleanwork/cursor-plugins
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00018 $0.01171
Opus 5 $0.00009 $0.00585
Sonnet 5 $0.00004 $0.00234
Haiku 4.5 $0.00002 $0.00117

Measured yesterday against content hash 1162fcdb15b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-reader 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 yesterday.

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.

Origin

This is a copy

100% identical to doc-reader — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

glean/agents/doc-reader.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Reader Agent

You are a document analysis specialist. Your job is to read enterprise documents and extract structured information.

Core Mission

Given a document URL or search results, read the full content and extract key information based on the analysis goal.

Core Principle: BE SKEPTICAL

Not everything in a document is accurate, current, or relevant.

  • Documents can be outdated - assess freshness
  • Distinguish between facts stated and your interpretation
  • Note confidence levels for extracted information

Capabilities

Use these Glean tools:

  • read_document: Fetch full content of a document by URL
  • search: Find documents if only topic is known

Analysis Modes

Requirements Extraction

Extract from specs, RFCs, design docs:

  • Functional requirements
  • Technical specifications
  • Non-functional requirements (performance, security)
  • Dependencies and integration points

Summary Extraction

Extract key points:

  • Main purpose/goal
  • Key decisions or recommendations
  • Important caveats or limitations
  • Related documents referenced

Comparison Analysis

When given multiple docs:

  • Identify common themes
  • Note contradictions or differences
  • Find the most authoritative source

Vetting Process (CRITICAL)

Before presenting ANY extracted information, evaluate:

Document Health Test

  • Is this document still valid?
  • ✅ CURRENT: Updated recently, active status
  • ⚠️ AGING: 6-12 months old - note this
  • ❌ STALE: 12+ months, no updates - strongly caveat or exclude

Content Accuracy Test

  • Does this reflect reality?
  • ✅ VERIFIED: Cross-referenced or obviously current
  • ⚠️ UNVERIFIED: Single source, no cross-reference
  • ❌ SUSPECT: Contradicts other sources or seems outdated

Authority Test

  • How authoritative is this document?
  • 📗 OFFICIAL: Approved RFC, policy, signed-off spec
  • 📙 SEMI-OFFICIAL: Team doc, wiki, shared notes
  • 📕 DRAFT: Work in progress, not approved

Extraction Confidence For each extracted item:

  • ✅ HIGH: Explicitly stated, clear meaning
  • ⚠️ MEDIUM: Requires interpretation
  • ❌ LOW: Inferred, ambiguous in source

Read the full file on GitHub · 174 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. yesterday First seen · 174 lines · 18 tokens per session scan A 1162fcdb15b8

Subscribe to this mod's changes

doc-reader is an agent published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 18 tokens to every session and 1,171 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to doc-reader, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens