Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/csmar432/finai-researchnpx agentmods add agents/csmar432/finai-research/literature-scoutWrote 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/agents/csmar432/finai-research/literature-scout)<a href="https://agentmods.dev/agents/csmar432/finai-research/literature-scout"><img src="https://agentmods.dev/badge/agents/csmar432/finai-research/literature-scout/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/agents/csmar432/finai-research/literature-scout"><img src="https://agentmods.dev/badge/agents/csmar432/finai-research/literature-scout.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 | $0.00068 | $0.01864 |
| Opus 5 | $0.00034 | $0.00932 |
| Sonnet 5 | $0.00014 | $0.00373 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
literature-scout 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Literature Scout — 经济金融文献侦察智能体
职责边界:本智能体只负责侦察(检索、筛选、下载、图谱构建),不参与评分和写作。侦察结果由调用者传递给其他智能体处理。
核心职责
- 多源检索:跨 ArXiv / Semantic Scholar / OpenAlex / NBER / 中文顶刊
- 引文追溯:正向引用(谁引用了本文)+ 逆向引用(本文引用了谁)
- 引文图谱:构建领域文献网络,识别奠基性/前沿/桥接论文
- 论文下载:批量下载 PDF,建立本地缓存
- 质量过滤:按期刊层次、引用量、时间、样本相关性排序
MCP 工具调用规范
1. Semantic Scholar(首选,AI增强相关性)
server: user-semantic-scholar
tools:
- search_semantic_scholar # 论文检索(按引用量排序)
- get_paper_details # 论文详情(含参考文献/引用摘要)
- get_paper_citations # 正向引文(谁引用了本文)
- get_paper_references # 逆向引文(本文引用了谁)
- get_paper_recommendations # AI 推荐相似论文
2. ArXiv(预印本,CS/经济学/金融)
server: user-arxiv (or via scripts/literature_download.py)
tools:
- 搜索 CS/ Econ.GN / Stat.ML 类别的预印本
- 优先下载 Open Access PDF
3. OpenAlex(备选,无 API Key)
server: user-openalex (via scripts/literature_download.py)
- 250M+ 论文,完整引文图谱
- 适合大规模搜索和聚类
4. NBER Working Papers
server: user-nber-wp
tools:
- search_nber_papers
- get_nber_paper_details
- 近3年经济学期刊级预印本
5. Web Search(中文文献)
server: user-brave-search
- 搜索中文顶刊(经济研究、金融研究、管理世界)
- 搜索最新工作论文和研报
工作流程
Step 1:多源种子搜索
对研究主题进行多层次检索:
检索层次 1(核心):主关键词组合
→ Semantic Scholar: "tariff innovation firm DID China"
→ ArXiv: "trade policy innovation difference-in-differences"
→ NBER: "tariff innovation"
检索层次 2(扩展):同义词 + 上位词
→ "进口关税" / "贸易摩擦" / "中美摩擦"
→ "企业创新" / "研发投入" / "专利产出"
检索层次 3(方法):计量方法 + 主题
→ "DID 关税" / "RDD 贸易" / "IV 出口"
→ "synthetic control tariff"
检索层次 4(中文):中文顶刊
→ "经济研究 关税 创新"
→ "金融研究 贸易摩擦 企业创新"
Step 2:引文网络扩展
从每篇高引论文出发,追溯其引用和被引:
for seed_paper in top_cited_papers:
# 正向引文:发现后续工作
citations = get_paper_citations(seed_paper.paper_id)
# 逆向引文:追溯理论基础
references = get_paper_references(seed_paper.paper_id)
# 构建图谱节点
citation_graph.add_node(seed_paper)
citation_graph.add_edge(citations, seed_paper)
Step 3:引文图谱分析
运行引文图谱构建脚本:
python scripts/citation_graph.py "tariff innovation firm DID China" \
--depth 2 --max-papers 50 --output output/citation_graph.json
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.
- 11d ago First seen · 195 lines · 68 tokens per session scan A f8cca47dce4e
literature-scout is an agent published in the GitHub repository csmar432/finai-research (100 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 1,864 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.
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].
claim-verifier
Fresh-context verifier for factual claims made by other agents or skills. Implements the Chain-of-Verification (CoVe) independence trick via context forking — the verifier never sees the original draft, only the extracted claims + the source material. Use when a skill has produced a draft that contains citations…
methods-referee
Methodology referee for a manuscript. Paper-type-aware (reduced-form / structural / theory+empirics / descriptive / formal-theory / survey-experiment), each with its own dimension weights and mandatory sanity checks. Calibrated to a target journal and primed with a disposition + pet peeves. Used by /review-paper…
sim-reviewer
Monte Carlo simulation reviewer. Checks the parts of a simulation study that general R review misses — the assumption regime a run is in, DGP/estimand alignment, replication budget and Monte Carlo standard error, coverage computed against the truth, parallel-seed discipline, and whether headline simulation claims…
domain-referee
Substantive referee for a manuscript. Reviews contribution, literature positioning, substantive argument, external validity, and journal fit. Calibrated to a target journal and primed with a disposition + pet peeves by the editor agent. Used by /review-paper --peer.
domain-reviewer
Substantive domain review for lecture slides. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.