literature-writing

literature-writing is a skill for Claude Code from yqi96/warranted. It costs 53 tokens per session (1,218 once invoked), scanned A, original, MIT.

Writing guidance for LaTeX text that cites published research papers, such as introductions, related-work sections, discussions, and surveys. It requires each cited claim to be represented and verified in an argument graph before it appears in the paper.

In plain words
What is it for?
Use it when searching for papers, checking sources, preparing BibTeX, or writing research prose that must cite published literature.
Why use it?
It prevents unsupported or poorly placed citations and keeps each research claim connected to the evidence that supports it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the warranted plugin — 7 skills, 8 agents, 1 hook, 1 MCP server shipped together

Good fit Use it when searching for papers, checking sources, preparing BibTeX, or writing research prose that must cite published literature.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yqi96/warranted/literature-writing
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.

Any agent
npx skills add yqi96/warranted --skill literature-writing
Clone the repo
git clone --depth 1 https://github.com/yqi96/warranted

Made for: Claude Code.

Or install warranted, the plugin that ships this one along with the rest of its 7 skills, 8 agents, 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 literature-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/yqi96/warranted/literature-writing/github.svg)](https://agentmods.dev/skills/yqi96/warranted/literature-writing)
Your own site
<a href="https://agentmods.dev/skills/yqi96/warranted/literature-writing"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/literature-writing/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-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/yqi96/warranted/literature-writing"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/literature-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 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 $0.00053 $0.01218
Opus 5 $0.00026 $0.00609
Sonnet 5 $0.00011 $0.00244
Haiku 4.5 $0.00005 $0.00122

Measured 12d ago against content hash 3ed5f9db52dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

literature-writing 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 12d 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.

skills/literature-writing/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graph Mapping

Never cite a paper directly. A citable proposition from a paper first becomes a source="literature" Statement (Ground role); LaTeX then cites that Statement with \cite{statement_N}, where N is the Statement's id. The citation is a pointer into the argument graph, not a bibliography shortcut.

citable proposition from a paper -> literature Statement (Ground role)
paragraph point                  -> Claim
why findings support the point   -> Warrant
methodological authority         -> Statement (Backing role)
conflicting paper finding        -> Statement (Rebuttal role)

Granularity:

  • one paper yields multiple Grounds when it offers multiple distinct citable propositions
  • one Ground carries multiple paper attachments when several papers support the same proposition
  • different findings, populations, methods, measurements, or scopes are separate Grounds
  • convergence across distinct Grounds is a Warrant's job, not a merge into a vague composite Ground

Obligations

Object-layer work in this channel — search, reading, download, BibTeX, prose edits — is valid only when it creates, verifies, cites, or reconciles a literature Statement (Ground role), or a Claim built from such Statements. A searched paper must become a Ground, Backing, or Rebuttal, or be discarded with a reason; it is never accumulated as an inert reading list.

Graph state Required action
No Claim for a load-bearing paragraph thesis create_claim, or update the existing Claim
A sentence cites a paper for a proposition Reuse a matching literature Statement, or create_statement(source="literature") and attach the paper
A paper provides several relevant propositions One create_statement(source="literature") per distinct proposition
Several papers support the same specific finding Attach them to the same Statement only when they support the same proposition
A literature Statement is cited but not verified Check the paper supports it, then update_node(verification="verified", attachments=[...])
A Claim has Grounds but no Warrant create_warrant(ground_ids=[...])
A Warrant needs authority create_statement(...), then update_node(<warrant>, backing_ids={add:[...]})
A paper contradicts the Claim or Warrant create_statement(rebuttal_for={target_id, target_type})
The text changes the paragraph thesis Reconcile the Claim
A citation points to the wrong Ground Point to the correct Statement, or create one; edit an existing Statement only to fix an error, never to fit the sentence
Existing LaTeX uses author-year keys Migrate each: identify the cited proposition, create/reuse its literature Statement, replace the key with statement_N

Read the full file on GitHub · 88 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. 12d ago First seen · 88 lines · 53 tokens per session scan A 3ed5f9db52dc

Subscribe to this mod's changes

literature-writing is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 1,218 once invoked, about $0.0003 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 skills, from other repositories

proof-checker

A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.

wanshuiyin/Auto-claude-code-research-in-sleep · 87 tokens

research-lit

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 48 tokens

auto-paper-improvement-loop

An automated editing cycle for a compiled research paper: an external language model reviews it, fixes are applied, and the paper is compiled again.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

paper-illustration

A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

paper-write

A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.

wanshuiyin/Auto-claude-code-research-in-sleep · 50 tokens

experiment-bridge

A workflow that turns an experiment plan into code, reviews the code, runs an initial check, deploys experiments, and collects early results. Deployment means sending the experiment to the environment where it will run, such as a GPU machine.

wanshuiyin/Auto-claude-code-research-in-sleep · 74 tokens