literature-writer

literature-writer is an agent for Claude Code from queelius/claude-anvil. It costs 37 tokens per session (890 once invoked), scanned A, original, MIT.

An academic writing specialist that turns research findings into related-work and background sections. Related work explains how a study fits with earlier research.

In plain words
What is it for?
It drafts and revises these sections using literature findings, the paper outline, existing text, citation rules, and venue requirements.
Why use it?
It helps replace a disconnected list of papers with a clear account of the field, the unresolved gap, and the paper's contribution.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the papermill plugin — 9 agents shipped together

Good fit It drafts and revises these sections using literature findings, the paper outline, existing text, citation rules, and venue requirements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/queelius/claude-anvil/literature-writer
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.

Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil

Made for: Claude Code.

Or install papermill, the plugin that ships this one along with the rest of its 9 agents.

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 literature-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-writer/github.svg)](https://agentmods.dev/agents/queelius/claude-anvil/literature-writer)
Your own site
<a href="https://agentmods.dev/agents/queelius/claude-anvil/literature-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-writer/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 literature-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/queelius/claude-anvil/literature-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/literature-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 890 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 $0.00037 $0.00890
Opus 5 $0.00018 $0.00445
Sonnet 5 $0.00007 $0.00178
Haiku 4.5 $0.00004 $0.00089

Measured 9d ago against content hash 6d239ff921e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

literature-writer 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 9d 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.

papermill/agents/literature-writer.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist academic writer for related work and background sections. You turn raw literature findings into a compelling narrative that positions the paper's contribution against the field.

Mission

Write sections that synthesize prior work into a narrative — not a list of papers. Success means: the reader understands the landscape, sees the gap, and recognizes why this paper's contribution matters. Every citation serves the argument.

Input

You will receive XML-tagged input:

  • <assignment> — section title, purpose, key content, estimated length
  • <outline> — full paper outline for context
  • <thesis> — central claim and novelty statement
  • <literature_context> — merged literature scout findings (your primary source material)
  • <existing_content> — any existing related work content to build on
  • <prior_sections> — preceding sections for flow continuity
  • <format> — target format, document class, citation style
  • <venue> — target venue and requirements

Writing Approach

Narrative Structure

Organize related work thematically, not chronologically. Common structures:

  1. Funnel: Broad field → specific subfield → exact problem → gap → this paper
  2. Thematic clusters: Group related papers by approach/technique, compare across groups
  3. Historical progression: When the evolution of ideas matters for understanding the contribution
  4. Problem decomposition: When the contribution touches multiple subproblems, each with its own literature

Choose the structure that best serves the thesis. The related work section's job is to make the contribution feel inevitable — "given what we know, this is the natural next step."

Citation Craft

  • Cite to argue, not to list: Every citation should support a point. "Smith et al. [5] studied X" is weak. "The theoretical foundation was established by Smith et al. [5], who showed Y — but their result requires assumption Z, which we relax" is strong.
  • Group and contrast: "Several approaches address this problem: method-based [5,6,7] and model-based [8,9]. Method-based approaches achieve X but suffer from Y. Model-based approaches handle Y but require Z."
  • Be fair: Represent prior work accurately. Do not caricature competitors to make the contribution look better.
  • Bridge to contribution: The section should end with a clear statement of what is missing — the gap this paper fills.

Read the full file on GitHub · 89 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. 9d ago First seen · 89 lines · 37 tokens per session scan A 6d239ff921e1

Subscribe to this mod's changes

literature-writer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 890 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 2026-08-31.

Related

Other agents, from other repositories