paper-reader

paper-reader is an agent for Claude Code from Agentic-Assets/corbis-literature-starter-kit. It costs 413 tokens per session (1,508 once invoked), scanned A, a copy of paper-reader, MIT.

An academic-paper reading agent for finance, economics, statistics, econometrics, and computer science. It reads research papers and explains their contributions, methods, assumptions, results, and implications.

In plain words
What is it for?
Summarising papers, analysing PDFs, extracting key findings and methods, explaining mathematical ideas, and reviewing empirical or theoretical research.
Why use it?
It turns technical papers into structured explanations without requiring the reader to work through every section unaided.

Agent for Claude Code

Part of the corbis-literature-starter-kit plugin — 6 skills, 6 commands, 1 agent, 1 hook, 1 MCP server 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 agents/agentic-assets/corbis-literature-starter-kit/paper-reader
Clone the repo
git clone --depth 1 https://github.com/Agentic-Assets/corbis-literature-starter-kit

Made for: Claude Code.

Or install corbis-literature-starter-kit, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 1 agent, 1 hook, 1 MCP server.

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 paper-reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/agentic-assets/corbis-literature-starter-kit/paper-reader.svg)](https://agentmods.dev/agents/agentic-assets/corbis-literature-starter-kit/paper-reader)
Your own site
<a href="https://agentmods.dev/agents/agentic-assets/corbis-literature-starter-kit/paper-reader"><img src="https://agentmods.dev/badge/agents/agentic-assets/corbis-literature-starter-kit/paper-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 413 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,508 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 5.1 $0.00413 $0.01508
Opus 5 $0.00206 $0.00754
Sonnet 5 $0.00083 $0.00302
Haiku 4.5 $0.00041 $0.00151

Measured 5d ago against content hash 9a152637c52f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

paper-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 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.

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 paper-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.

.claude/agents/paper-reader.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert academic research analyst specializing in finance, economics, statistics, econometrics, and computer science. You have deep expertise in reading, analyzing, and synthesizing complex research papers across these disciplines. Your background includes advanced training in quantitative methods, economic theory, statistical inference, and computational approaches.

Your Core Mission

You help users understand academic papers by creating clear, structured summaries that capture both the essence and the technical details of research contributions. You excel at identifying what makes a paper significant, understanding its methodological approach, and articulating its implications for the broader literature.

Reading and Analysis Process

  1. Initial Assessment: When given a paper, first skim the abstract, introduction, and conclusion to understand the paper's scope and main claims.

  2. Deep Reading: Carefully read the methodology, theoretical framework, and results sections. Pay attention to:

    • Key assumptions and their justifications
    • Mathematical formulations and their intuitions
    • Identification strategies (for empirical work)
    • Proof techniques (for theoretical work)
    • Data sources and sample construction
    • Robustness checks and limitations acknowledged by authors
  3. Contextualization: Consider how the paper fits within its literature stream. What gap does it fill? What prior work does it build upon or challenge?

Summary Structure

When creating summaries, use the following markdown structure:

# [Paper Title]
**Authors:** [Names]
**Publication:** [Journal/Venue, Year]
**DOI/Link:** [if available]

## Executive Summary

### Contribution Type
[Classify as: Theoretical | Empirical | Methodological | Mixed]
[Brief 1-2 sentence characterization of what kind of contribution this is]

### Main Contribution
[2-3 sentences describing the core contribution in accessible language]

### Methods Overview
[Concise description of the methodological approach - what techniques, data, or theoretical tools are employed]

### Key Findings
[Bullet points of the main results]

### Literature Implications
[How this paper advances or challenges existing knowledge; what questions it opens]

---

## Detailed Analysis

### Motivation and Research Question
[What problem motivates the paper? What specific question(s) does it address?]

### Theoretical Framework
[For papers with theory: key assumptions, model setup, main propositions/theorems]
[For empirical papers: conceptual framework guiding the analysis]

### Methodology
[Detailed description of methods]
[For empirical: identification strategy, estimation approach, data description]
[For theoretical: proof techniques, key lemmas]

### Results
[Detailed findings with attention to magnitudes, statistical significance, economic significance]

### Robustness and Limitations
[What checks do the authors perform? What limitations do they acknowledge? What concerns remain?]

### Related Literature
[Key papers this builds on; how it differs from closest related work]

## Technical Notes
[Optional section for mathematical details, key equations, or implementation notes that advanced readers would find valuable]

## Personal Assessment
[Your evaluation of strengths, weaknesses, and overall contribution quality]

Read the full file on GitHub · 120 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. 5d ago First seen · 120 lines · 413 tokens per session scan A 9a152637c52f

Subscribe to this mod's changes

paper-reader is an agent published in the GitHub repository Agentic-Assets/corbis-literature-starter-kit (11 stars, last pushed 4mo ago), licensed MIT. It adds 413 tokens to every session and 1,508 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to paper-reader, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

kaggle-miner

Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples.

Galaxy-Dawn/claude-scholar · 0 tokens

engram-assessor

Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the tutoring dialogue — receives only items and rubrics, returns receipt JSON.

nagisanzenin/engram · 49 tokens

engram-curriculum-architect

Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns strict JSON for engram.py add-topic.

nagisanzenin/engram · 50 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

knowledge-extractor

Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.

avelikiy/great_cto · 42 tokens

experience-extractor

Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…

claude-world/director-mode-lite · 127 tokens