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.
npx skills add malue-ai/dazee-small --skill paper-searchgit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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/malue-ai/dazee-small/paper-search)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/paper-search"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/paper-search/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/malue-ai/dazee-small/paper-search"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/paper-search.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 | $0.00029 | $0.00670 |
| Opus 5 | $0.00015 | $0.00335 |
| Sonnet 5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade C, and why
paper-search scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=large+language+model+agent&limit=10&fields=title,abstract,year,citationCount,authors,url" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=large+language+model+agent&limit=10&fields=title,abstract,year,citationCount,authors,url" | python3 -c " What it actually says
学术论文搜索
搜索学术论文,支持 Semantic Scholar、CrossRef 等开放 API(无需 API Key)。
使用场景
- 用户说「帮我搜一下关于 XXX 的论文」「找几篇 LLM Agent 的最新论文」
- 用户需要论文的摘要、引用数、BibTeX
- 用户需要了解某个研究领域的最新进展
搜索方式
Semantic Scholar(推荐,免费,无需 Key)
# 搜索论文
curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=large+language+model+agent&limit=10&fields=title,abstract,year,citationCount,authors,url" | python3 -c "
import json, sys
data = json.load(sys.stdin)
for i, paper in enumerate(data.get('data', []), 1):
title = paper.get('title', '')
year = paper.get('year', '?')
citations = paper.get('citationCount', 0)
authors = ', '.join(a.get('name', '') for a in paper.get('authors', [])[:3])
url = paper.get('url', '')
print(f'{i}. [{year}] {title}')
print(f' 作者: {authors}')
print(f' 引用: {citations} | {url}')
print()
"
获取论文详情
# 通过论文 ID 获取详情(含摘要)
curl -s "https://api.semanticscholar.org/graph/v1/paper/{paper_id}?fields=title,abstract,year,citationCount,authors,references,url" | python3 -m json.tool
获取 BibTeX
# 通过 DOI 获取 BibTeX
curl -sH "Accept: application/x-bibtex" "https://doi.org/{doi}"
CrossRef(通过 DOI 搜索)
curl -s "https://api.crossref.org/works?query=transformer+attention&rows=5" | python3 -c "
import json, sys
data = json.load(sys.stdin)
for item in data.get('message', {}).get('items', []):
title = item.get('title', [''])[0]
doi = item.get('DOI', '')
year = item.get('published', {}).get('date-parts', [['']])[0][0]
print(f'[{year}] {title}')
print(f' DOI: {doi}')
print()
"
输出规范
- 展示前 5-10 篇最相关论文
- 每篇包含:标题、作者(前 3 位)、年份、引用数、链接
- 用户要求时提供 BibTeX
- 如果有摘要,展示前 200 字
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.
- 9d ago First seen · 80 lines · 29 tokens per session scan C f9a715373b06
paper-search is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 670 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…