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 VectorPeak/vectorpeak-agent-skills --skill zhihu-clippings-vpgit clone --depth 1 https://github.com/VectorPeak/vectorpeak-agent-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/vectorpeak/vectorpeak-agent-skills/zhihu-clippings-vp)<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/zhihu-clippings-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/zhihu-clippings-vp/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/vectorpeak/vectorpeak-agent-skills/zhihu-clippings-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/zhihu-clippings-vp.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 | $0.00094 | $0.01787 |
| Opus 5 | $0.00047 | $0.00894 |
| Sonnet 5 | $0.00019 | $0.00357 |
| Haiku 4.5 | $0.00009 | $0.00179 |
Grade A, and why
zhihu-clippings-vp 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zhihu Clippings
When To Use
Use this skill for Zhihu clipping tasks where the user needs saved Markdown source material, including:
- locating a Zhihu author or article from a person name, people URL, article URL, title, screenshot/OCR, copied snippet, or mixed clues
- clipping zhuanlan articles into grouped Obsidian-style Markdown files
- clipping a known Zhihu answer from a question/answer URL or explicit
--question-idplus--answer-id - using screenshot/OCR or copied text as search clues, while avoiding screenshot-only final clippings
Do not use this skill for browser scraping, captcha/cookie workflows, or downstream wiki rewriting/classification.
Core Contract
Run official-first, TikHub-final:
- Use Zhihu Developer Platform
zhihu_searchfirst for coarse positioning, author/content identity, article ID/source checks, and metadata cross-checks. - Use TikHub only as the final fulltext provider when official search returns summaries or when article/answer body fidelity matters.
- Mark TikHub direct fetches as third-party content.
--article-idand--answer-idcan fetch through TikHub directly, but those paths are not official verification by themselves. Prefer official search verification before or after the direct fetch when possible; otherwise record/report that official verification was not completed. - Never create a final clipping from screenshot/OCR text, copied snippets, or official
ContentTextwhen the user expects a full article/answer body. Use those inputs as search/disambiguation clues only. - Stop and report clearly when neither official search can identify the target nor TikHub can return a complete untruncated body.
Generated Markdown should land in 01.raw/01.Inbox by default as unprocessed source material. Do not summarize, rewrite, classify, or move it into 02.wiki unless the user explicitly asks for that downstream step.
For detailed Markdown QA rules, heading normalization, code fence cleanup, and provider notes, read references/zhihu-notes.md when preparing or reviewing final output.
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.
- 11d ago First seen · 147 lines · 94 tokens per session scan A cd594504c898
zhihu-clippings-vp is a skill published in the GitHub repository VectorPeak/vectorpeak-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,787 once invoked, about $0.0005 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
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
preprep
A Korean-language presentation-preparation workflow that develops a topic through questions, proposes several story structures, and keeps slides, speaker notes, scripts, and related documents aligned.
mxMigrateToDb
Use when the user says "/mxMigrateToDb", "migrate to db", "migrate local docs to mcp", "sync local docs", "import docs to knowledge db", "--extract-backlog", "extract legacy backlog", or otherwise wants to import local docs/.md fallback files into the MCP Knowledge-DB. Runs after MCP outages (when offline-fallback…
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.
memstack-business-scope-of-work
Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.
validate
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.