What is literature AGENTS.md?

Documentation for a standalone system that searches academic literature, manages PDFs and references, and summarizes research papers with language models. It describes the system's structure, components, and tests.

Use it when working on paper discovery, PDF management, reference tracking, summaries, citations, or the system's scripts and infrastructure.

It explains how the research workflow fits together and keeps this repository independent from other manuscript or template projects.

literature AGENTS.md — Instructions file for Codex and OpenCode by docxology: Documentation for a standalone system that searches academic l

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/docxology/literature/agents-md

Clone the repo

git clone --depth 1 https://github.com/docxology/literature

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/docxology/literature/agents-md.svg)](https://agentmods.dev/instructions/docxology/literature/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/docxology/literature/agents-md"><img src="https://agentmods.dev/badge/instructions/docxology/literature/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,892 This file is loaded in full into every session.

When invoked 2,892 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.

Model	Per session	Once invoked
Fable 5.1	$0.02892	$0.02892
Opus 5	$0.01446	$0.01446
Sonnet 5	$0.00578	$0.00578
Haiku 4.5	$0.00289	$0.00289

Measured 5d ago against content hash 8741fb359684, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

literature AGENTS.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 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.

AGENTS.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Literature Search and Management System - Documentation

Overview

This is a standalone repository for academic literature search, PDF management, reference tracking, and LLM-powered paper summarization. The system provides a workflow from paper discovery to analysis and citation management.

System Architecture

Standalone Design

This repository is independent and self-contained:

No dependencies on external template or manuscript systems
Duplicated shared infrastructure (infrastructure/core/, infrastructure/llm/) for independence
Separate bibliography (data/references.bib) from any manuscript system
Test suite for all functionality

Directory Structure

literature/
├── run_literature.sh              # Main orchestrator (interactive menu)
├── scripts/                        # Orchestrator scripts
│   ├── literature_search.py      # Literature search orchestrator
│   └── bash_utils.sh               # Shared bash utilities
├── infrastructure/                 # Core modules
│   ├── __init__.py                 # Package exports
│   ├── core/                       # Foundation utilities (duplicated)
│   │   ├── logging_utils.py       # Logging system
│   │   ├── exceptions.py          # Exception hierarchy
│   │   ├── config_loader.py        # Configuration management
│   │   ├── progress.py             # Progress tracking
│   │   └── ...
│   ├── llm/                        # LLM integration (duplicated)
│   │   ├── core.py                 # LLM client
│   │   ├── templates.py            # Prompt templates
│   │   └── ...
│   └── literature/                 # Literature-specific modules
│       ├── core/                   # Core search functionality
│       ├── sources/                # API adapters (arXiv, Semantic Scholar, etc.)
│       ├── pdf/                    # PDF handling
│       ├── library/                 # Library management
│       ├── workflow/                # Workflow orchestration
│       ├── summarization/          # AI summarization
│       ├── meta_analysis/           # Meta-analysis tools
│       └── ...
├── tests/                          # Test suite
│   └── infrastructure/
│       ├── core/                   # Core tests (filtered)
│       ├── llm/                    # LLM tests (filtered)
│       └── literature/             # Literature-specific tests
├── data/                           # Data directory
│   ├── library.json                # Paper metadata index
│   ├── references.bib              # BibTeX bibliography
│   ├── summarization_progress.json # Summarization progress tracking
│   ├── failed_downloads.json      # Failed download tracking
│   ├── pdfs/                       # Downloaded PDFs
│   ├── summaries/                  # AI-generated summaries
│   ├── extracted_text/             # Extracted PDF text
│   ├── embeddings/                 # Cached embedding files (JSON)
│   └── output/                     # Meta-analysis outputs
└── docs/                           # Documentation

Read the full file on GitHub · 404 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.

5d ago First seen · 404 lines · 2,892 tokens per session scan A 8741fb359684

Subscribe to this mod's changes

literature AGENTS.md is an instructions file published in the GitHub repository docxology/literature (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 2,892 tokens to every session, about $0.0145 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.

Research academic active-inference bibliography ecology literature-review papers

literature AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Literature Search and Management System - Documentation

Overview

System Architecture

Standalone Design

Directory Structure

What this file has done since we first saw it

Other instructions, from other repositories

AI-Powered-Literature-Review-Skills AGENTS.md

phd-deepread-workflow CLAUDE.md

openalex-research-mcp CLAUDE.md

phd-deepread-workflow AGENTS.md

al-folio javascript-scripts.instructions.md

polish-academic-mcp context7.instructions.md