comparing-papers

comparing-papers is a skill for Claude Code, Codex from chgagne/claude-skills-research. It costs 91 tokens per session (1,316 once invoked), scanned A, original, MIT.

A guide for comparing a research draft directly with specific earlier papers. It puts methods and experiments side by side on details such as training scale, protocols, and random seeds.

In plain words
What is it for?
Use it to compare baselines and competing methods, document evidence from both papers, calculate training-scale ratios and seed counts, and identify differences that reviewers may question.
Why use it?
It helps reveal whether a claimed comparison is fair and whether the draft and prior work used meaningfully different experimental conditions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to compare baselines and competing methods, document evidence from both papers, calculate training-scale ratios and seed counts, and identify differences that reviewers may question.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chgagne/claude-skills-research/comparing-papers
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 chgagne/claude-skills-research --skill comparing-papers
Clone the repo
git clone --depth 1 https://github.com/chgagne/claude-skills-research

Made for: Claude Code, Codex.

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 comparing-papers

README.md
[![agentmods](https://agentmods.dev/badge/skills/chgagne/claude-skills-research/comparing-papers/github.svg)](https://agentmods.dev/skills/chgagne/claude-skills-research/comparing-papers)
Your own site
<a href="https://agentmods.dev/skills/chgagne/claude-skills-research/comparing-papers"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/comparing-papers/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 comparing-papers

Your own site · 80×15
<a href="https://agentmods.dev/skills/chgagne/claude-skills-research/comparing-papers"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/comparing-papers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 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 $0.00091 $0.01316
Opus 5 $0.00046 $0.00658
Sonnet 5 $0.00018 $0.00263
Haiku 4.5 $0.00009 $0.00132

Measured 11d ago against content hash 304b62cb0f46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

comparing-papers 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 11d ago.

The scan reads SKILL.md. This mod also ships 14 executable files (assets/compare/__init__.py, assets/compare/__main__.py, assets/compare/assemble.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

comparing-papers/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comparing Papers

Overview

Puts a draft and its closest prior work side by side on the axes reviewers attack, with every cell traceable to a quoted sentence and the section it came from.

The tool gathers evidence; you draw the conclusion. It computes a note on exactly two axes — a training-scale ratio and a seed count — because those are arithmetic. On every other axis it shows two passages and stops. "These protocols differ" reads like a finding but is a judgement, and a tool that makes it will eventually make it wrongly in a document you sign your name to.

This automates the check reviewing-paper-sources/reference/claim-audit.md calls "baseline training scale vs its published scale", which otherwise means reading two appendices and doing a multiplication.

Run it

python3 ~/.claude/skills/comparing-papers/assets/run-compare.py . \
    --against "SNIP: Bridging Mathematical Symbolic and Numeric Realms" \
    --out review-assets/

# take the shortlist straight from a gap sweep
python3 ~/.claude/skills/comparing-papers/assets/run-compare.py . \
    --from-candidates review-assets/candidates.json --grade THREAT

Run by absolute path from the paper directory. Stdlib only. --against accepts a title, a DOI or an arXiv id and repeats; --limit caps how many papers are fetched (default 5).

Writes paper-comparison-<date>.md and comparison.json. Exit code 2 means some paper was reachable only as an abstract.

The acquisition ladder

1. arXiv e-print source  LaTeX, read with stdlib tarfile/gzip
2. arXiv PDF             via pdftotext, only if that binary is installed
3. open-access PDF       via OpenAlex oa_url, same caveat
4. abstract              degraded

LaTeX source leads for a reason. Training scale, seed counts and compute budgets live in appendices, and appendices are what PDF extraction mangles. Rung 1 needs no PDF parsing at all and keeps section headings exact. On the SNIP paper it yields 66 sections including "Pre-training Data Details"; the number the whole comparison turns on is in there.

Read the full file on GitHub · 110 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. 11d ago First seen · 110 lines · 91 tokens per session scan A 304b62cb0f46

Subscribe to this mod's changes

comparing-papers is a skill published in the GitHub repository chgagne/claude-skills-research (4 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 1,316 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 2026-08-31.

Related

Other skills, from other repositories

paper-writer

Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…

kgraph57/paper-writer-skill · 106 tokens

food-research

Run a comprehensive, multi-source literature and evidence-synthesis workflow for food & nutrition science. Use when the user wants to research a food/nutrition topic in depth, do a literature review, build an evidence brief, screen and synthesize many sources, verify citations, or scope a systematic review.…

PangenomeAI/academic-skills-food-nutrition · 154 tokens

food-paper

Multi-subagent manuscript system for food & nutrition science covering the whole research process: understand the field, frame research questions, curate and analyze data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal-aware throughout. Includes a…

PangenomeAI/academic-skills-food-nutrition · 180 tokens

food-pipeline

Master orchestrator for the whole food & nutrition research-to-publication workflow. Coordinates the specialist skills — each with its own subagent set — into one governed path: journal selection, research (food-research / food-deep-research), writing & analysis (food-paper), figures (food-figure), peer review…

PangenomeAI/academic-skills-food-nutrition · 137 tokens

food-deep-research

General-purpose deep research that produces a fully written, source-validated literature review on any question: scope it, design the method, discover and screen sources by journal ranking, validate every source, extract and verify evidence, synthesize, stress-test, then write and format the review (APA 7.0 by…

PangenomeAI/academic-skills-food-nutrition · 166 tokens

food-figure

Comprehensive figure system for food & nutrition manuscripts: analyzes the user's data, recommends the best figure(s) to make, then produces submission-grade graphics in Python or R at the target journal's spec. Handles all common scientific figure types (bar/box/violin, line/kinetic, scatter/regression, Bland–Altman…

PangenomeAI/academic-skills-food-nutrition · 218 tokens