novelty-check

novelty-check is a skill for Claude Code from AutoResearch-Factory/Agon. It costs 63 tokens per session (573 once invoked), scanned A, original, MIT.

A research process for checking whether a research idea or proposal is genuinely new. It compares the idea's main technical claims with work found in arXiv, Google Scholar and Semantic Scholar, then rates each claim.

In plain words
What is it for?
Use it to extract the core claims of a proposal, search for related papers, inspect recent conference and preprint work, and grade novelty as high, medium or low.
Why use it?
It helps identify work that already uses the same method or makes a similar claim before time is spent developing it. It also separates a new method from a potentially new finding or application.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the agon plugin — 5 skills, 4 commands, 12 agents, 2 hooks shipped together

Good fit Use it to extract the core claims of a proposal, search for related papers, inspect recent conference and preprint work, and grade novelty as high, medium or low.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autoresearch-factory/agon/novelty-check
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 AutoResearch-Factory/Agon --skill novelty-check
Clone the repo
git clone --depth 1 https://github.com/AutoResearch-Factory/Agon

Made for: Claude Code.

Or install agon, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 12 agents, 2 hooks.

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 novelty-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/autoresearch-factory/agon/novelty-check/github.svg)](https://agentmods.dev/skills/autoresearch-factory/agon/novelty-check)
Your own site
<a href="https://agentmods.dev/skills/autoresearch-factory/agon/novelty-check"><img src="https://agentmods.dev/badge/skills/autoresearch-factory/agon/novelty-check/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 novelty-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/autoresearch-factory/agon/novelty-check"><img src="https://agentmods.dev/badge/skills/autoresearch-factory/agon/novelty-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00063 $0.00573
Opus 5 $0.00032 $0.00287
Sonnet 5 $0.00013 $0.00115
Haiku 4.5 $0.00006 $0.00057

Measured 11d ago against content hash 8d28a17693aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

novelty-check 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.

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.

skills/novelty-check/SKILL.md · 53 lines

What it actually says

这是一个挑剔的research reviewer系统性检查一个工作的核心贡献是否新颖的流程.

流程

1. Extract Core Claims

Identify 3-5 core technical claims that would need to be novel:

  • What is the method?
  • What problem does it solve?
  • What is the mechanism?
  • What makes it different from obvious baselines?

2. Multi-Source Literature Search

For each core claim, search broadly:

  • sources: arXiv / Google Scholar / Semantic Scholar
  • Use specific technical terms from the claim
  • Try at least 3 different query formulations per claim
  • Always check the most recent 6 months of arXiv — the field moves fast
  • 顶会近期核查: 明确看最近的 ICLR, NeurIPS, ICML 等会议的相关子领域的 proceedings 和 accepted papers

3. 判断 novelty

对每个 claim 打一个 novelty 等级:

  • HIGH: 没查到实质重叠的工作, claim 是原创机制
  • MEDIUM: 存在相关工作, 但 application / scope / mechanism 有明显区别
  • LOW: 已有高度相似工作, 或本质上是 "Apply X to Y" 且 application 没揭示意外洞见

Key Rules

  • Be brutally honest — false novelty claims waste months of research time.
  • "Applying X to Y" is NOT novel unless the application reveals surprising insights.
  • Check both the method AND the experimental setting for novelty.
  • If the method is not novel but the FINDING would be, say so explicitly.
  • web search / metadata 摘要只是线索, 不是证据. 所有进入报告的论文引用必须用 arxiv tool / arxiv skill 下载并阅读 tex/full text 核验.
  • 最终报告 novelty check 部分的字数在 200-300 words 左右.

不要在此停下

novelty check 只是某个 reviewer workflow 的第 1 步. 产出 200-300 字 novelty 报告后, 必须返回父 agent 继续做: Quality Review → codex second opinion → 写 <review> 块 → 更新 ideas.xml / proposals.xml. 不要把 novelty check 的报告当成最终交付物而 end_turn.

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 · 53 lines · 63 tokens per session scan A 8d28a17693aa

Subscribe to this mod's changes

novelty-check is a skill published in the GitHub repository AutoResearch-Factory/Agon (47 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 573 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 2026-08-30.

Related

Other skills, from other repositories