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 qisehong/wechat-to-obsidian-skill --skill wechat-to-obsidiangit clone --depth 1 https://github.com/qisehong/wechat-to-obsidian-skillWrote 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/qisehong/wechat-to-obsidian-skill/wechat-to-obsidian)<a href="https://agentmods.dev/skills/qisehong/wechat-to-obsidian-skill/wechat-to-obsidian"><img src="https://agentmods.dev/badge/skills/qisehong/wechat-to-obsidian-skill/wechat-to-obsidian/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/qisehong/wechat-to-obsidian-skill/wechat-to-obsidian"><img src="https://agentmods.dev/badge/skills/qisehong/wechat-to-obsidian-skill/wechat-to-obsidian.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 | $0.00107 | $0.01522 |
| Opus 5 | $0.00053 | $0.00761 |
| Sonnet 5 | $0.00021 | $0.00304 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
wechat-to-obsidian scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Downloads the article HTML via curl (iOS Safari User-Agent for WeChat compatibility) How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save WeChat Articles to Obsidian
Download a WeChat official account article and save it as a Markdown note in an Obsidian vault. A single command handles download, extraction, conversion, and cleanup. Optionally auto-syncs to a Git remote.
Quick Start
python scripts/save_wechat.py "https://mp.weixin.qq.com/s/xxxxx"
# With Git auto-sync (commit + push after saving)
python scripts/save_wechat.py --git-sync "https://mp.weixin.qq.com/s/xxxxx"
The script saves to the vault inbox configured via one of these methods (highest priority first):
--vault-pathcommand-line argumentOBSIDIAN_VAULT_INBOXenvironment variable~/.wechat-to-obsidian.confconfiguration file- Interactive prompt on first run
See references/configuration.md for detailed setup instructions.
What the Script Does
- Downloads the article HTML via curl (iOS Safari User-Agent for WeChat compatibility)
- Extracts title, account name, and publish date from the page metadata
- Extracts the article body using JsContentExtractor (HTMLParser depth tracking — see Why not regex?)
- Converts the body HTML to Markdown (preserves images, links, headings, code blocks, lists)
- Writes a
.mdfile with Obsidian frontmatter to the vault inbox - Optionally commits and pushes to a Git remote (
--git-sync) - Removes temporary files
Why not regex?
⚠️ Pitfall: regex-based
js_contentextraction fails silently on WeChat HTML.WeChat HTML frequently has
<div>attributes that span multiple lines:<div class="rich_media_content js_underline_content" id="js_content">A regex like
id="js_content"(.*?)</div>will not match this — theidattribute is on a different line from the tag opening. The result is a silently empty body with no error message.JsContentExtractor uses Python's
HTMLParserto track tag nesting depth and reliably captures the full body regardless of attribute formatting. Regex is kept only as a last-resort fallback.
What ships with it
2 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.
- 12d ago First seen · 168 lines · 107 tokens per session scan A 736d7f43341f
wechat-to-obsidian is a skill published in the GitHub repository qisehong/wechat-to-obsidian-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,522 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.