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.
curl -O https://raw.githubusercontent.com/Guo-Chenxu/paper-agent/main/.claude/skills/reviewer-attack/SKILL.mdgit clone --depth 1 https://github.com/Guo-Chenxu/paper-agentWrote 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.
[](https://agentmods.dev/skills/guo-chenxu/paper-agent/reviewer-attack)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01189 |
| Opus 5.5 | $0.00023 | $0.00476 |
| Sonnet 5.5 | $0.00011 | $0.00238 |
| Haiku 4.5 | $0.00006 | $0.00119 |
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 yesterday.
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.
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.
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.
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.
- yesterday Changed · +10 lines 7dc6c7deb42b
- 2mo ago First seen · 100 lines · 57 tokens per session scan A f4243e1405c8
reviewer-attack is a skill published in the GitHub repository Guo-Chenxu/paper-agent (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,189 once invoked, about $0.0002 per session on Opus 5.5. 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.
reviewer-attack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reviewer-attackGuo-Chenxu/paper-agent | Skill | 4 | 2d ago | Apache-2.0 | A | 57 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |