paperpush: Skill for Claude Code

.claude/skills/paperpush-autofill/SKILL.md

paperpush-autofill is a skill for Claude Code from pachterlab/paperpush. It costs 98 tokens per session (2,427 once invoked), scanned A, original, BSD-2-Clause.

A manuscript-file tool that fills a journal or preprint service submission file from papers, author details, figures, and supplementary files. It writes the extracted information into a venue-specific .sub file.

In plain words
What is it for?
Use it to prepare a .sub file from a directory containing your manuscript materials. It is useful when submitting research to a supported venue, such as bioRxiv, a public server for sharing scientific papers before formal journal publication.
Why use it?
It removes the need to copy submission details by hand and helps avoid overwriting protected fields or creating an invalid file.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is pachterlab/paperpush's own configuration. It tells Claude Code how to work on paperpush itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paperpush configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pachterlab/paperpush. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pachterlab/paperpush/main/.claude/skills/paperpush-autofill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pachterlab/paperpush

Made for: Claude Code.

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 paperpush-autofill

README.md
[![agentmods](https://agentmods.dev/badge/skills/pachterlab/paperpush/paperpush-autofill.svg)](https://agentmods.dev/skills/pachterlab/paperpush/paperpush-autofill)
Your own site
<a href="https://agentmods.dev/skills/pachterlab/paperpush/paperpush-autofill"><img src="https://agentmods.dev/badge/skills/pachterlab/paperpush/paperpush-autofill.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,427 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 $0.00098 $0.02427
Opus 5 $0.00049 $0.01213
Sonnet 5 $0.00020 $0.00485
Haiku 4.5 $0.00010 $0.00243

Measured 7d ago against content hash bfc39d48711c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

paperpush-autofill 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 7d 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.

.claude/skills/paperpush-autofill/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

paperpush autofill (Claude skill)

Populate a <venue>.sub file from a directory of manuscript files. You read the files and decide the values; the paperpush autofill command does all the writing, gating, and validation, so you cannot accidentally overwrite a policy field or produce an invalid file. Your job is extraction, not writing.

First: make sure you have a directory

The manuscript directory is required. If the skill was invoked on its own, without a directory in the user's message, stop and ask the user to provide the path to their manuscript directory before doing anything else — do not guess, do not scan the repository for candidate folders, and do not fall back to test fixtures. A good prompt is:

Which directory holds your manuscript files? Tell me the path, and (if you can) which file is the manuscript, which is the title page with authors and affiliations, where the figures are, and any supplements.

Only once the user has given you a directory should you continue. If they also named the venue, use it; otherwise infer or ask per the inputs below.

Inputs you need

  1. The venue slug (e.g. biorxiv). If the user did not say, ask, or infer it from a <slug>.sub filename they mention. Confirm it is supported with paperpush --venues.
  2. The manuscript directory and what each file is. Ask the user to describe the directory if they have not, for example: "manuscript.pdf is the paper, title_page.pdf has the authors and affiliations, figures are in figures/, supplement.pdf is supplementary material." If they just give a folder, list it and propose a mapping from the filenames, then confirm before extracting. Author names, emails, affiliations, and ORCIDs come out far more reliably from a title page or LaTeX/Word source than from a flattened PDF, so prefer those when present.

Steps

  1. Get the field schema and roles (the source of truth for what to fill):

    paperpush schema <venue>
    

Read the full file on GitHub · 194 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. 7d ago First seen · 194 lines · 98 tokens per session scan A bfc39d48711c

Subscribe to this mod's changes

paperpush-autofill is a skill published in the GitHub repository pachterlab/paperpush (163 stars, last pushed 5d ago), licensed BSD-2-Clause. It adds 98 tokens to every session and 2,427 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

pydicom

Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.

K-Dense-AI/scientific-agent-skills · 56 tokens

pptx-posters

Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.

K-Dense-AI/scientific-agent-skills · 59 tokens

extracting-lab-tables

Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…

maziyarpanahi/openmed · 210 tokens

paper-spine

Build, rewrite, audit, submit, revise, or transfer scholarly papers end to end, producing verified LaTeX/PDF/Word and target-specific publication packages.

WUBING2023/PaperSpine · 37 tokens

paper-compile

A build workflow that turns LaTeX source files into a PDF and checks whether the paper compiles correctly. LaTeX is a text-based system commonly used for academic papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 53 tokens

nsfc-budget

A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.

huangwb8/ChineseResearchLaTeX · 138 tokens