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 wechat-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/wechat-clippings-vp)<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/wechat-clippings-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/wechat-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/wechat-clippings-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/wechat-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 | $0.00088 | $0.03047 |
| Opus 5.5 | $0.00035 | $0.01219 |
| Sonnet 5.5 | $0.00018 | $0.00609 |
| Haiku 4.5 | $0.00009 | $0.00305 |
Grade A, and why
wechat-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 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Clippings
When To Use
Use this skill for personal-knowledge clipping of public WeChat Official Account articles into Markdown. Accepted inputs include direct mp.weixin.qq.com URLs, a public-account name, author/nickname, article title, screenshot OCR text, copied search/page text, or mixed instructions such as "clip the latest three articles about Agent from this account".
Do not use this skill for WeChat Official Account owner APIs, draft/publishing workflows, logged-in browser scraping, captcha handling, or paywall/access-control bypasses.
Core Workflow
Use TikHub-first mode. TikHub is a third-party provider, not an official WeChat API; response shape, quota, and coverage may drift.
- Parse the request into article URLs, account clues, title keywords, optional screenshot/OCR titles, and output-directory requirements.
- If direct
mp.weixin.qq.comURLs are present, treat them as the complete scope and call TikHub article-detail endpoints directly. - If no direct URL is present, search the official account with
fetch_search_official_account, preferjumpInfo.userNamevalues shaped likegh_..., then callfetch_mp_article_list. - Paginate article lists with
data.offset.Offsetuntil the requested titles are found, the requested count is satisfied, orIsEnd == 1. - For screenshot/OCR batches, prefer account list plus fuzzy title matching. Avoid long-title
fetch_search_articleuntil account-list discovery fails. - Use article-list records only as candidate metadata. Fetch final full text through TikHub v2 article detail:
POST /api/v1/wechat_mp/v2/fetch_article_detailwith JSON{ "url": "...", "raw": false }. - Convert the article body from
#js_contentor structured detail fields into Markdown, preserving source URLs, images, tables, formulas, code blocks, and readable text. - Cache raw TikHub responses for QA, but never print or write the API key.
For difficult runs, use parallel analysis if useful: one pass to identify account/title candidates, one pass to inspect TikHub response fields, and one pass to QA the staged Markdown. The script also supports parallel article-detail fetches with --workers; keep the output article order identical to the user input order.
What ships with it
4 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 · 222 lines · 88 tokens per session scan A 5bca946af14d
wechat-clippings-vp is a skill published in the GitHub repository VectorPeak/vectorpeak-agent-skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 3,047 once invoked, about $0.0004 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
live-transcript-summary
A real-time note-taking skill that watches audio transcription in the current WPS note and periodically organizes it. WPS is an office and note-taking application.
grok-sync
A tool for importing conversations from an official Grok data export into an Obsidian vault. Grok is xAI's chat service, and Obsidian is a note-taking application; the import creates notes and a local database.
granola-sync
Pull fresh meetings from Granola (summaries, transcripts, participants) into an Obsidian vault over the official API. Incremental and idempotent by note id and updatedat, so re-runs make no duplicates. Triggers: "/granola-sync", "pull granola", "refresh meetings".
Wikimate Link
A note-linking workflow for Obsidian, an app for storing linked Markdown notes. It finds clearly related notes and can group notes on one topic into a table-of-contents note.
anywrite
Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.
template-execute
Execute a Templater template, optionally writing the rendered output to a new file. Arguments are exposed to the template via tp.mcpTools.prompt("key") (directly under tp, NOT under tp.user — easy footgun). EN triggers: "render the X template", "run the daily template", "execute Templates/X.md with arg1=v1", "use…