reviewing-paper-sources

reviewing-paper-sources is a skill for Claude Code, Codex from chgagne/claude-skills-research. It costs 119 tokens per session (6,285 once invoked), scanned A, original, MIT.

A guide for reviewing an academic paper from its LaTeX source files or, when necessary, a PDF. It treats review as an evidence-gathering process involving calculations, reference checks, source compilation, and figure rendering.

In plain words
What is it for?
Use it for internal paper reviews or neutral referee reports, including checking reported numbers, compiling the paper, auditing citations, and producing review files.
Why use it?
It helps uncover problems that casual reading can miss, such as stale PDFs, unsupported statistics, incorrect references, or figures that do not work at print size.

Skill for Claude CodeCodex

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

Good fit Use it for internal paper reviews or neutral referee reports, including checking reported numbers, compiling the paper, auditing citations, and producing review files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chgagne/claude-skills-research/reviewing-paper-sources
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 reviewing-paper-sources
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 reviewing-paper-sources

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/chgagne/claude-skills-research/reviewing-paper-sources"><img src="https://agentmods.dev/badge/skills/chgagne/claude-skills-research/reviewing-paper-sources.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00119 $0.06285
Opus 5 $0.00060 $0.03143
Sonnet 5 $0.00024 $0.01257
Haiku 4.5 $0.00012 $0.00628

Measured 7d ago against content hash 8b2b26e7dc23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reviewing-paper-sources scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 7 executable files (assets/pdfshim/__init__.py, assets/pdfshim/refs.py, assets/pdfshim/structure.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

(`curl -sL arxiv.org/e-print/<id> | tar -xz`, or CVF/ACL Anthology for camera-readies), and
reviewing-paper-sources/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing Paper Sources

Overview

A paper review is an evidence-gathering exercise, not a reading exercise. The findings that change a paper come from things you compute or verify, not from things you notice while reading: recomputing the headline statistic, checking every reference against its publisher record, compiling the sources yourself, rendering the figures at print size.

Core principle: never trust an artifact you did not produce. The committed PDF is stale until proven current. A reference is wrong until checked against a primary source. A reported rate means nothing until you have its sample size.

Mode: establish this first

Mode A — internal Mode B — external
Situation Advisor/self-review of your own group's draft Referee report for a venue
Register Blunt, shared stake in the outcome Neutral, addressed to authors + chair
Proposes fixes Yes, including edits to the sources No — diagnose only, never rewrite the authors' text
Artifacts Review .md + .pdf, *-annotated.tex, refs-corrected.bib Review .md + .pdf only
Scores/verdict Yes (both modes) Yes

If it is ambiguous, ask. "My student's paper" ⇒ Mode A. "I'm reviewing for X" ⇒ Mode B.

Then establish what you were given. With LaTeX sources, follow the workflow below as written. With only a PDF — the usual case for refereeing — the compile step, the .bbl cross-check and the source-based tools are all unavailable, and two failure modes appear that do not exist otherwise. Build the pseudo-source first and read reference/pdf-only-review.md:

python3 assets/run-pdfshim.py paper.pdf --out review-assets/

Also establish where in its lifecycle the paper is, because it changes what the review is for: pre-submission (triage by what fits the deadline), already submitted (target what reviewers will attack, and prepare answers), or post-rejection (framing and structural weaknesses).

An unfinished draft is a fourth case, and it needs the findings split three ways: content, not-yet-written, and container. Content is the only one that bears on the judgement — claims that are written and wrong, framing the paper's own data refutes, work missing from the argument. Container is everything that makes the artifact submittable rather than good, and it belongs in its own late section with the severity tag saying so ("Blocks submission; not a judgement on the work") rather than sitting at the top of the concerns list outranking the science. The temptation runs the other way, because container defects are the easiest to find and the easiest to state with certainty — which is exactly why they crowd out the findings that took real work to establish.

Read the full file on GitHub · 297 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 Changed · +18 lines 8b2b26e7dc23
  2. 12d ago First seen · 279 lines · 119 tokens per session scan A 865a32728414

Subscribe to this mod's changes

reviewing-paper-sources is a skill published in the GitHub repository chgagne/claude-skills-research (4 stars, last pushed 7d ago), licensed MIT. It adds 119 tokens to every session and 6,285 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.