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 | $0.00176 | $0.02078 |
| Opus 5 | $0.00088 | $0.01039 |
| Sonnet 5 | $0.00035 | $0.00416 |
| Haiku 4.5 | $0.00018 | $0.00208 |
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 8d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gleaner(Skill + CLI)
用本机仓库统一 CLI 做三线学术文献采集。
安装 skill = 先下载项目(禁止只拷 SKILL.md)
用户说「安装 skill / 注册 skill / 装 gleaner」时,第一条命令必须是 clone 仓库。
没有 gleaner_cli.py 就还没装完。只拷本文件到 ~/.cursor/skills/gleaner 无效。
# 用户指定了目录就用那个;否则当前工作区下的 gleaner\
git clone https://github.com/liuqiaodongdong/gleaner.git <dest>
cd <dest>
python -m pip install -r requirements.txt
python gleaner_cli.py install-skill
$env:GLEANER_ROOT = (Resolve-Path .).Path
python gleaner_cli.py status
本机已有仓库:在仓库根跑 python gleaner_cli.py install-skill。
Skill 目录里已有脚本时:python scripts/bootstrap.py(没有仓库会自己 clone)。
然后才能录 cookie、再采集。
录 cookie(Agent 自己做,不要问用户拖滑块)
status 里 cookies.ok=false 或用户说「登录 / 录 cookie」时:
- 先确认
.env有CJY_USER/CJY_PASS/CJY_SOFTID(没有则协助写好,再status)。 - Agent 自己启动(不要只跑
login-hint,不要让用户手拖或从 DevTools 复制):- 首次无文件:
$env:ACQ_BROWSER_CHANNEL='msedge'; $env:ACQ_ALLOW_COLD_LOGIN='1'; python login.py - 已有文件(批间重录):只设
ACQ_BROWSER_CHANNEL=msedge,再python login.py
- 首次无文件:
login.py内部用超级鹰 9602 过滑块并立刻写cookies.json。Agent 不要另调超级鹰 API、不要用浏览器工具抠 cookie。- 终端出现
已更新会话后重跑status,再采。无个人知网账号。
官方仓库:https://github.com/liuqiaodongdong/gleaner.git
需要 Python 3.11+。知网线建议 Windows + 系统 Edge。
clone + install-skill 之后设 GLEANER_ROOT,再 status。线未 ready → 配 .env;无 cookie → Agent 自己跑 login.py。不要未就绪就硬采。
$env:GLEANER_ROOT = "<本仓库绝对路径>"
python "$env:GLEANER_ROOT\gleaner_cli.py" status
pwsh "$env:USERPROFILE\.grok\skills\gleaner\scripts\gleaner.ps1" status
子命令:install-skill | status | sources | score | login-hint | prepare | cnki-list | cnki | els | intl
默认根目录
优先级:GLEANER_ROOT → CLI --root → Skill 目录 .gleaner_root(包装脚本)→ 仓库内 gleaner_cli.py 所在目录。详见 references/env.md。
铁律
-
先 status:任何采集前必须先跑
python "$env:GLEANER_ROOT\gleaner_cli.py" status
看lines.*.ready/blockers/next_steps_for_user。线未 ready → 引导配置,禁止硬采。 -
知网先录 cookie:
status里cookies.ok=false时 禁止 跑cnki/cnki-list。Agent 必须自己启动python login.py(超级鹰在脚本里自动过滑块并写盘)。禁止:只打印login-hint就停、让用户手拖滑块、让用户从浏览器复制 cookie、用浏览器工具抠 cookie、另外调用超级鹰接口。仅第一次没有文件才加ACQ_ALLOW_COLD_LOGIN=1。冷启动采集下不了全文,只会空烧超级鹰。
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.
- 8d ago Changed · +42 lines · +87 tokens per session 56b70de9eb96
- 12d 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 12d ago), licensed MIT. It adds 176 tokens to every session and 2,078 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
openalex-researcher
Use the OpenAlex MCP to search 250M+ scholarly works, retrieve author profiles, analyze institutional output, explore journal sources, and aggregate citation trends — all from the world's largest free and open scholarly database.
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…
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…
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.