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 liuqiaodongdong/gleaner --skill gleanergit clone --depth 1 https://github.com/liuqiaodongdong/gleanerWrote 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/liuqiaodongdong/gleaner/gleaner)<a href="https://agentmods.dev/skills/liuqiaodongdong/gleaner/gleaner"><img src="https://agentmods.dev/badge/skills/liuqiaodongdong/gleaner/gleaner/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/liuqiaodongdong/gleaner/gleaner"><img src="https://agentmods.dev/badge/skills/liuqiaodongdong/gleaner/gleaner.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 | $0.00083 | $0.01132 |
| Opus 5.5 | $0.00033 | $0.00453 |
| Sonnet 5.5 | $0.00017 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
gleaner 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 today.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gleaner 普通版
仓库：https://github.com/liuqiaodongdong/gleaner.git，分支 main。只提供 CNKI 与 Elsevier 两条线路。
安装与更新
新安装先克隆完整仓库，不能只复制 SKILL.md。已有仓库先检查 Git 状态，再更新 main。
git clone https://github.com/liuqiaodongdong/gleaner.git <dest>
cd <dest>
python -m pip install -r requirements.txt
python gleaner_cli.py install-skill
python gleaner_cli.py status
需要 Python 3.11+；Windows 建议系统 Edge。技能注册到各客户端的 skills/gleaner，.gleaner_root 指向本仓库，与 gleanera 独立。根目录优先使用 CLI --root，其次 GLEANER_ROOT；包装脚本可读取技能指针。
网络与首次验证
- 默认直连，校园网或 VPN 的系统路由仍生效；无需代理软件或端口。
ACQ_PROXY仅在用户确实需要代理时配置，不自动读取系统代理。不能把PORT占位符填入有效配置。 status检查本地配置，不能据此宣称机构权限或远端账号已验证。- 首次填写实际
CJY_USER、CJY_PASS、CJY_SOFTID，运行python gleaner_cli.py score验证账号和积分。占位值不算已配置；报错先修正，不能直接开始验证码调用。 - 无
cookies.json时，由 Agent 运行python login.py --first-run。以后运行python login.py复用已有会话。Windows 自动选择 Edge；其它平台须安装 Playwright 浏览器或指定ACQ_BROWSER_CHANNEL。 - 登录脚本内部完成超级鹰调用与平稳拖动，Agent 不另调打码接口，也不重复操纵同一个验证页面。自动最多两次；失败返回非零退出码，报告实际原因，不把退出或创建文件视为成功。
- 默认不切换为人工等待。只有用户明确选择人工验证，才临时设置
ACQ_MANUAL_CAPTCHA=1，人工等待最多 90 秒。 - 确认登录输出
ok=true并保存非空会话后，再运行status。未就绪时不能启动采集；机构权限仍由实际访问结果验证。
采集
先 status，根据需要选择线路，不自动转用其它来源。
CNKI 完整题录
python gleaner_cli.py cnki-list --details --query "数字经济" --num 50 --out-name demo_metadata
输出标题、作者、摘要、关键词、期刊、日期、机构、基金、被引次数、下载次数、URL 共 11 列。仅访问列表和详情，不下载全文、不创建 papers；使用 --num，不用 --until。不要与全文批次复用输出目录。省略 --details 为列表页 7 列。
CNKI 全文
由 Agent 拓展概念组，prepare 生成 L1–L4 检索式；先 cnki-list 看命中数，再 cnki。L1 不够可升 L2；L3/L4 经用户明确同意后使用。
目标篇数为用户指定或列表 TOTAL。使用同一 --out-name 和 --until <目标> 串行多批，每批 40–60 篇随机；不要一次拉满、不要并行浏览器。普通版批间可自动热启动登录脚本，失败即停止。只有 until_reached 和实际文件数满足目标才报告采够。
Elsevier
只使用官方 Developer API，Key 来自 https://dev.elsevier.com/apikey/manage 。支持英文布尔式、概念组及期刊分级。默认保存完整 PDF＋XML；PDF 通过正文对象接口下载并验证身份及可用页数。PDF 失败时保留 XML 并报告原因，不能计为完整下载。
运行与汇报
长任务用终端 CLI，不擅自增加固定超时；查看 corpus/*_run.log。汇报 local_dir、metadata_rows、实际 PDF/CAJ 或 XML 数量、主要标题和日志。零下载和部分失败如实报告。
What ships with it
5 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.
- today Changed · -53 lines · -87 tokens per session 69c6038dc4b1
- 7d ago Changed · -6 tokens per session 0ef44d3648a6
- 1mo ago Changed · +42 lines · +87 tokens per session 56b70de9eb96
- 1mo ago First seen · 76 lines · 89 tokens per session scan A b7f50895b9d5
gleaner is a skill published in the GitHub repository liuqiaodongdong/gleaner (3 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,132 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
openalex-researcher
Search and analyze scholarly literature via OpenAlex (250M+ works, 300M+ authors, 100K+ institutions, 250K+ journals/sources — free, CC0, no paywall). Use this skill whenever the user wants to find academic papers, look up a researcher's publication record or h-index, audit a university's research output, discover…
scopus-researcher
Expert academic researcher using the Scopus MCP. Finds papers, retrieves full abstracts, builds author profiles, analyzes citation impact, and constructs advanced Boolean queries across the Elsevier Scopus database. Activate when asked to search for academic papers, analyze research trends, find citations, profile…
research-skill
An academic research skill for finding, analysing, and reviewing scholarly literature. Scholarly literature includes published research papers and related academic sources.
super-research
Autonomous research skill for open-ended, high-volume research work — an agent left running for a while (minutes to overnight) that produces honest, comparable, auditable evidence instead of a single one-shot answer. Covers eight modes selected by the request: (1) experiment loop — iteratively edit code, run, measure…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…