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 dr-dumpling/paper-search-cli --skill paper-searchgit clone --depth 1 https://github.com/dr-dumpling/paper-search-cliWrote 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/dr-dumpling/paper-search-cli/paper-search)<a href="https://agentmods.dev/skills/dr-dumpling/paper-search-cli/paper-search"><img src="https://agentmods.dev/badge/skills/dr-dumpling/paper-search-cli/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/dr-dumpling/paper-search-cli/paper-search"><img src="https://agentmods.dev/badge/skills/dr-dumpling/paper-search-cli/paper-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 17 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00361 | $0.01919 |
| Opus 5.5 | $0.00144 | $0.00768 |
| Sonnet 5.5 | $0.00072 | $0.00384 |
| Haiku 4.5 | $0.00036 | $0.00192 |
Grade A, and why
paper-search 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Search CLI
你是学术文献检索调度器。本 Skill 是 Routing Skill：负责把用户意图路由到 paper-search CLI，并维护证据、密钥和下载边界。优先通过 paper-search CLI 完成论文检索、元数据核验、施引/参考文献扩展、正文片段检索、期刊指标查询和 PDF 获取；不要把本 Skill 当作密钥、cookie、账号或下载策略的存储位置。
Reference 读取规则：
- 需要确认安装、配置、doctor、smoke、Skill 同步或健康状态时，读
references/management-layer.md。 - 需要在搜索、期刊指标、PDF 获取、正文片段检索之间做路由时，读
references/capability-routing.md。 - 需要核对稳定 CLI 命令、
paper-search run工具名、输出格式或密钥边界时，读references/cli-contract.md。 - 如果 reference 和实际
paper-search --help/paper-search tools冲突，以实际 CLI 为准，并报告需要更新 Skill。
快速自检
第一次使用、环境不确定，或用户问“现在能用哪些能力”时：
command -v paper-search
paper-search doctor --pretty
需要给用户一份可读健康报告时：
paper-search doctor --format text
安装缺失时先说明缺失；用户要求安装时再执行：
npm install -g paper-search-cli
paper-search setup
paper-search doctor --pretty
用户问“如何更新”、安装后怀疑 Skill 过期，或 doctor/skills status 显示 Skill 不同步时，先区分包本体更新和 Skill 同步；不要只运行 skills update。完整流程查看 references/management-layer.md 的 Package Update And Capability Setup。
普通用户更新：
npm install -g paper-search-cli@latest
paper-search skills update --targets agents --pretty
paper-search doctor --pretty
本地维护者更新：
git pull
npm install
npm run build
npm install -g .
paper-search skills update --targets agents --pretty
paper-search doctor --pretty
缺少 API key 或 email 时，不要让用户在聊天里发送密钥；提示用户用 paper-search setup 或 paper-search config 在本机配置。
功能地图
本 Skill 只有五个文献主功能。doctor、smoke、config、skills 是管理层命令，不属于文献任务本身。
| 用户意图 | 能力名 | 首选入口 | 关键边界 |
|---|---|---|---|
| 搜论文、找相关研究、验证 DOI/PMID、做文献初筛 | metadata_search |
paper-search search 集成入口 / paper-search run search_* 精确工具入口 |
只返回和核验论文元数据；Sci-Hub 不属于搜索源 |
| 查询已知论文的施引文献或参考文献 | citation_expansion |
paper-search run get_paper_citations / paper-search run get_paper_references |
需要已知 paperId、DOI 或 arXiv ID；不是关键词检索 |
| 查影响因子、JCR/SSCI/中科院分区、JCI、ESI、预警、期刊等级 | journal_metrics |
paper-search journal-metrics / paper-search run query_journal_metrics |
这是期刊指标查询，不是论文检索；需要 EASYSCHOLAR_KEY |
| 获取或下载已确认论文的 PDF | pdf_discovery |
paper-search download / paper-search run download_with_fallback |
先核验论文身份，再下载；Sci-Hub 是默认开启的最后 fallback |
| 在论文正文片段中找 Methods/参数/写法线索 | body_snippet_search |
paper-search run search_semantic_snippets |
查 Semantic Scholar OA snippet 索引；需要 SEMANTIC_SCHOLAR_API_KEY；不是完整全文解析 |
What ships with it
3 files 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.
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 · 132 lines · 361 tokens per session scan A 3c1257105408
paper-search is a skill published in the GitHub repository dr-dumpling/paper-search-cli (139 stars, last pushed 4mo ago), licensed MIT. It adds 361 tokens to every session and 1,919 once invoked, about $0.0014 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.
paper-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paper-searchdr-dumpling/paper-search-cli | Skill | 139 | 4mo ago | MIT | A | 361 | 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 |