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 zjp1997720/zhijian-skills --skill web-clippergit clone --depth 1 https://github.com/zjp1997720/zhijian-skillsWrote 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/zjp1997720/zhijian-skills/web-clipper)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/web-clipper"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/web-clipper/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/zjp1997720/zhijian-skills/web-clipper"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/web-clipper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00134 | $0.03841 |
| Opus 5.5 | $0.00054 | $0.01536 |
| Sonnet 5.5 | $0.00027 | $0.00768 |
| Haiku 4.5 | $0.00013 | $0.00384 |
Grade A, and why
web-clipper 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Clipper
目标:把「网页文章收藏」做成稳定工作流,而不是一次性手工操作。
和 Obsidian / 本地知识库的关系
本 Skill 是文章进入本地知识系统的入口。它不把网页直接冒充成已经整理好的知识,而是先保存为带来源信息的 source_candidate,供后续人工筛选、知识编译或写作流程继续处理。
默认分工:
- Obsidian Web Clipper:浏览器里手动剪藏,模板负责生成最小 OKF frontmatter。
- 本 skill:Agent 批量抓取、补抓失败页面、检查文章正文质量。
- 后续知识流程:把高价值候选资料编译成来源卡、概念、方法、案例、练习或写作素材。
新增或抓取的文章默认不是“已整理知识”,而是“待判断资料”。状态字段使用:
unprocessed -> queued -> source_carded -> compiled -> used
ignored / needs_human
保存的 Markdown 应尽量包含以下字段,方便 Obsidian、检测脚本和后续 Agent 读取:
---
type: source_candidate
title: "..."
summary: "..."
source: "https://..."
resource: "https://..."
source_kind: web_article
platform: web
author: "..."
published: "YYYY-MM-DD"
clipped: "ISO时间"
clipper: agent_web_clipper
okf_version: local-okf-v0.2
compile_status: queued
status: unprocessed
training_relevance: medium
topics:
- Agent
candidate_outputs:
- source_card
- writing_fuel
reuse_note: ""
tags:
- clipping
---
字段含义:
type: source_candidate:表示这是候选来源,不是正式 Wiki 页。source_kind:来源类型,例如wechat_article、x_status、web_article。training_relevance:内容复用相关度。Agent 抓取默认medium,可用--training-relevance high|medium|low|unknown覆盖。topics:OKF 主题标签。脚本会从标题、URL、描述和 tags 粗推,也可用--topic Agent --topic AI培训显式指定。candidate_outputs:后续可能拆成的知识资产类型。脚本默认source_card+writing_fuel,可用--candidate-output method等重复追加。compile_status:后续自动检测和编译流程读取的主状态字段。Agent 抓取默认queued,表示进入候选队列但不自动写正式 Wiki。
这个 skill 解决什么问题
它覆盖两类任务:
-
单篇收藏
- 输入一个文章 URL
- 提取标题、摘要、发布日期、正文
- 保存为 Markdown 到用户指定目录
-
批量收藏
- 输入一个索引页、归档页、专题页、作者主页
- 按用户要求抓前 N 篇、热门文章、最新文章,或指定的一组文章
- 批量保存到本地
成功率优先的执行策略
按下面顺序走,不要反过来:
首次使用与依赖自检
这个 skill 在分享 zip 给别人后,统一走 wrapper,不要直接打主脚本。
首次运行时,先执行:
bash <web-clipper-root>/scripts/run_web_clipper.sh --help
注意:这条命令有副作用。
它会先运行 bootstrap,可能创建默认 clipping 目录和当前项目下的 .web-clipper/EXTEND.md。
wrapper 会先调用 scripts/bootstrap.sh,自动做这些事:
- 检查 Python 3 是否可用
- Python 3 缺失时尝试自动安装
- 检查主脚本是否完整
- 自动创建默认 clipping 目录
- 首次运行时写入当前项目下的
.web-clipper/EXTEND.md
What ships with it
8 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 · 437 lines · 134 tokens per session scan A 9d0821fa583a
web-clipper is a skill published in the GitHub repository zjp1997720/zhijian-skills (787 stars, last pushed 4d ago), licensed MIT. It adds 134 tokens to every session and 3,841 once invoked, about $0.0005 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.
web-clipper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| web-clipperzjp1997720/zhijian-skills | Skill | 787 | 4d ago | MIT | A | 134 | Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | today | MIT | A | 40 | Claude Code |