What is paper-source-scraper?

A paper-search tool that finds recent research papers on configured topics, authors, and arXiv subject areas. arXiv is a public website where researchers share papers, often before formal publication.

Use it for recurring research searches, such as daily paper monitoring, with results saved as a list of newly found papers.

It removes the need to manually repeat searches and check which results have already appeared in earlier runs. It returns only papers that are new after two rounds of duplicate checking.

paper-source-scraper — Skill for Claude Code and Codex by AkaliKong

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 AkaliKong/PaperClaw --skill paper-source-scraper

Clone the repo

git clone --depth 1 https://github.com/AkaliKong/PaperClaw

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-source-scraper/github.svg)](https://agentmods.dev/skills/akalikong/paperclaw/paper-source-scraper)

Your own site

<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-source-scraper"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-source-scraper/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-source-scraper"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-source-scraper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 853 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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.00853
Opus 5.5	$0.00020	$0.00341
Sonnet 5.5	$0.00010	$0.00171
Haiku 4.5	$0.00005	$0.00085

Measured 2mo ago against content hash cb3c34e2c66f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-source-scraper 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 2mo 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/paper-source-scraper/SKILL.md · 104 lines

What it actually says

Paper Source Scraper — 靶向搜索与去重

概述

本 Skill 是一个纯数据获取工具，不包含任何 LLM 逻辑。所有逻辑放在 scripts/source_scraper.py 中确定性执行。

⚠️ 关键规则

纯脚本驱动：触发后直接执行 Python 脚本，Agent 不需要参与搜索和去重逻辑。
两级去重：搜索结果必须经过单次运行内去重（Intra-run）和跨周期增量去重（Cross-run）。
增量输出：最终输出仅包含真正的新论文，已在之前 run 中见过的论文会被过滤。

工作流程

执行搜索 — "搜索最新论文"

执行搜索脚本：

python $PAPER_AGENT_ROOT/scripts/source_scraper.py --run-id {run_id}

脚本将：

从 profile.yaml 读取关键词列表、白名单作者列表、arXiv 分类列表、时间范围
对每组关键词调用 ArxivSearcher.search() 执行搜索
对白名单作者额外执行按作者维度搜索
执行两级去重：
- Intra-run：对本次多组搜索结果基于 arXiv ID 去重合并
- Cross-run：与 seen_papers.json + seed_papers.json 做 Diff，过滤已见论文
将新增论文 ID 注册到 seen_papers.json
输出 skill1_search_results.json + 去重统计摘要

输入

profile.yaml 中的搜索配置：
- keywords：关键词列表
- whitelist_authors：白名单作者列表
- arxiv_categories：arXiv 分类列表
- search_days：搜索时间范围
seen_papers.json：全局已见论文注册表
seed_papers.json：核心论文目录

输出

skill1_search_results.json

{
  "papers": [
    {
      "arxiv_id": "2603.01234",
      "title": "...",
      "authors": ["..."],
      "abstract": "...",
      "url": "https://arxiv.org/abs/2603.01234",
      "source": "keyword_search",
      "published_date": "2026-03-01",
      "categories": ["cs.IR", "cs.AI"],
      "comments": ""
    }
  ],
  "stats": {
    "total_raw": 50,
    "dedup_intra_run": 35,
    "dedup_cross_run": 12,
    "new_increment": 12
  }
}

错误处理

场景	处理策略
arXiv API 频率限制（429）	指数退避重试（最多 3 次）
网络连接失败	返回空列表 + 错误日志
`seen_papers.json` 不存在或损坏	从 `paper_index.json` + `seed_papers.json` 重建

去重统计示例

搜索统计:
  原始搜索结果:     50 篇
  运行内去重后:     35 篇 (去除 15 篇重复)
  跨周期去重后:     12 篇 (去除 23 篇已见)
  最终增量新论文:   12 篇

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

README.md 1.4 KB

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.

2mo ago First seen · 104 lines · 51 tokens per session scan A cb3c34e2c66f

Subscribe to this mod's changes

paper-source-scraper is a skill published in the GitHub repository AkaliKong/PaperClaw (22 stars, last pushed 8mo ago), licensed MIT. It adds 51 tokens to every session and 853 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 2026-08-30.

Research Scientific

paper-source-scraper next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
paper-source-scraperAkaliKong/PaperClaw	Skill	22	8mo ago	MIT	A	51	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code