paper-agent: Skill for Claude Code

.claude/skills/reviewer-attack/SKILL.md

reviewer-attack is a skill for Claude Code from Guo-Chenxu/paper-agent. It costs 57 tokens per session (1,010 once invoked), scanned A, original, Apache-2.0.

A skeptical review process for research papers, experiment plans, results, and research ideas.

In plain words
What is it for?
Use it before finalizing research work to get strict, constructive, and newcomer-focused feedback.
Why use it?
It exposes weaknesses in correctness, importance, and clarity by asking independent reviewers with different perspectives to score the work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is Guo-Chenxu/paper-agent's own configuration. It tells Claude Code how to work on paper-agent 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 paper-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Guo-Chenxu/paper-agent. 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/Guo-Chenxu/paper-agent/main/.claude/skills/reviewer-attack/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Guo-Chenxu/paper-agent

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 reviewer-attack

README.md
[![agentmods](https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/reviewer-attack/github.svg)](https://agentmods.dev/skills/guo-chenxu/paper-agent/reviewer-attack)
Your own site
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/reviewer-attack"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/reviewer-attack/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 reviewer-attack

Your own site · 80×15
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/reviewer-attack"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/reviewer-attack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,010 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 $0.00057 $0.01010
Opus 5 $0.00028 $0.00505
Sonnet 5 $0.00011 $0.00202
Haiku 4.5 $0.00006 $0.00101

Measured 9d ago against content hash f4243e1405c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer-attack 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.

.claude/skills/reviewer-attack/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Attack Skill

When To Use

This skill is the adversarial review engine for the entire pipeline. Use it on:

  • Papers: LaTeX drafts, PDFs, or any written manuscript
  • Experiments: Experimental designs, results reports, ablation studies
  • Ideas: Research proposals, innovation claims, technical approaches

Whenever an artifact needs a skeptical, multi-perspective evaluation, invoke this skill.

Review Approach

This skill launches three independent, context-free reviewer agents. Each agent is a fresh instance with no prior knowledge — they see the target artifact exactly as a real reviewer would when encountering it for the first time. No shared context, no mutual influence.

Reviewer Personas

All three agents run in parallel:

Agent Focus Default Bias
Strict Reviewer Rigor, correctness, reproducibility Skeptical, looks for flaws
Constructive Reviewer Novelty, significance, improvement potential Wants to find value
Newcomer Reviewer Clarity, readability, accessibility Admits confusion, asks "naive" questions

0–5 Scoring System

Each reviewer scores the target across five dimensions, each rated 0 (worst) to 5 (best):

Dimension 0 1–2 3 4 5
Novelty No new ideas Minor tweak Incremental advance Significant novelty Groundbreaking
Rigor Fatal flaws Major gaps Adequate Solid, minor gaps Watertight
Clarity Unreadable Hard to follow Understandable with effort Clear and well-structured Crystal clear
Significance Trivial Niche interest Moderate impact Important contribution Field-changing
Feasibility Impossible Unlikely to work Plausible Well-justified Demonstrated

For papers, all five dimensions apply. For experiments, prioritize Rigor, Clarity, Feasibility. For ideas, prioritize Novelty, Significance, Feasibility.

Read the full file on GitHub · 100 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 · 100 lines · 57 tokens per session scan A f4243e1405c8

Subscribe to this mod's changes

reviewer-attack is a skill published in the GitHub repository Guo-Chenxu/paper-agent (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,010 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens