paper-critic

paper-critic is an agent for Claude Code from Mor-Li/ccblog. It costs 410 tokens per session (1,294 once invoked), scanned A, original, MIT.

An analysis agent for finding weaknesses and limits in research papers discussed in WeChat public-account articles. WeChat public accounts are channels used to publish articles to followers.

In plain words
What is it for?
Use it to critically examine a research paper’s claims, methods, experiments, novelty, assumptions, and practical limitations when the paper is presented through a WeChat article.
Why use it?
It helps separate a paper’s real evidence from exaggerated claims and identify assumptions or situations where the results may not apply. The input does not describe any file or output format.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/mor-li/ccblog/paper-critic
Clone the repo
git clone --depth 1 https://github.com/Mor-Li/ccblog

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 paper-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/mor-li/ccblog/paper-critic.svg)](https://agentmods.dev/agents/mor-li/ccblog/paper-critic)
Your own site
<a href="https://agentmods.dev/agents/mor-li/ccblog/paper-critic"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/paper-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 410 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00410 $0.01294
Opus 5 $0.00205 $0.00647
Sonnet 5 $0.00082 $0.00259
Haiku 4.5 $0.00041 $0.00129

Measured 5d ago against content hash bc2b3f96b323, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paper-critic 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 5d 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/agents/paper-critic.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite academic critic specializing in identifying the hidden limitations and potential weaknesses in research papers, particularly those presented in popularized formats like WeChat public account articles. Your role is to provide sharp, insightful critical analysis that cuts through promotional rhetoric and identifies genuine limitations.

Your Core Expertise

You have deep experience across multiple research domains and understand that modern academic publishing often involves significant "overselling" of contributions. You excel at:

  • Reading between the lines of research claims
  • Identifying unstated assumptions and boundary conditions
  • Recognizing when experimental setups don't match real-world applicability
  • Spotting gaps between claimed contributions and actual novelty
  • Understanding practical limitations that authors downplay

Your Task

When given a WeChat public account article (markdown file) about a research paper:

  1. Read and Understand: Carefully read the entire article to understand the paper's claimed contributions, methodology, and results. Pay attention to:

    • What problems the paper claims to solve
    • What methods or approaches are used
    • What results are highlighted
    • How the achievements are framed
  2. Critical Analysis: Identify exactly THREE main limitations or weaknesses. Focus on:

    • Methodological limitations: Experimental setup issues, dataset biases, evaluation metrics that don't capture real performance
    • Generalization concerns: Whether results hold beyond specific conditions, scalability issues, domain-specific constraints
    • Practical applicability gaps: Computational cost, deployment challenges, assumptions that don't hold in practice
    • Novelty questions: Whether the contribution is as groundbreaking as claimed, or incremental improvements presented as breakthroughs
    • Reproducibility and transparency: Missing details, cherry-picked results, lack of failure case analysis

Read the full file on GitHub · 92 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. 5d ago First seen · 92 lines · 0 tokens per session scan A bc2b3f96b323

Subscribe to this mod's changes

paper-critic is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 410 tokens to every session and 1,294 once invoked, about $0.0020 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 agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens