wechat-article-search

wechat-article-search is a skill for Claude Code from RongchangLi/pocketskill. It costs 35 tokens per session (654 once invoked), scanned B, original, MIT.

A search skill for public WeChat account articles, returning article titles, summaries, publication times, source accounts, and links.

In plain words
What is it for?
Use it to find articles by keyword and gather their metadata and URLs.
Why use it?
It removes the need to search WeChat references manually when collecting Chinese-language articles and their basic details.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; reads ~/.codex paths; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node tools/wechat-search/wx_search.mjs "<keyword>" -n 10.

Part of the my-skill plugin — 12 skills shipped together

Good fit Use it to find articles by keyword and gather their metadata and URLs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/RongchangLi/pocketskill
agentmods
npx agentmods add skills/rongchangli/pocketskill/wechat-article-search

Made for: Claude Code.

Or install my-skill, the plugin that ships this one along with the rest of its 12 skills.

Wrote 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.

agentmods badge for wechat-article-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/rongchangli/pocketskill/wechat-article-search/github.svg)](https://agentmods.dev/skills/rongchangli/pocketskill/wechat-article-search)
Your own site
<a href="https://agentmods.dev/skills/rongchangli/pocketskill/wechat-article-search"><img src="https://agentmods.dev/badge/skills/rongchangli/pocketskill/wechat-article-search/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.

agentmods 80×15 button for wechat-article-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/rongchangli/pocketskill/wechat-article-search"><img src="https://agentmods.dev/badge/skills/rongchangli/pocketskill/wechat-article-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00654
Opus 5.5 $0.00014 $0.00262
Sonnet 5.5 $0.00007 $0.00131
Haiku 4.5 $0.00003 $0.00065

Measured 2mo ago against content hash 10eef1b8bfee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

wechat-article-search scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find ~/pocketskill/plugins/my-skill ~/.codex/plugins/cache/pocketskill/my-skill ~/.claude/plugins/cache/pocketskill/my-skill -path "*/tools/wechat-search/wx_search.mjs" -print
plugins/my-skill/skills/my-skills/wechat-article-search/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wechat Article Search

Instructions

Use this skill when the user asks to search WeChat public account articles, find Chinese WeChat references, collect article links, or return article metadata such as title, summary, publish time, source account, and URL.

This skill is a wrapper around the shared tool:

tools/wechat-search/wx_search.mjs

Do not duplicate the search implementation inside this skill. Other skills may reuse the same shared tool.

Tool Location

Resolve the tool from the current Pocket Skill plugin root when possible:

node tools/wechat-search/wx_search.mjs "<keyword>" -n 10

If the current working directory is not the plugin root, locate the tool before running it:

find ~/pocketskill/plugins/my-skill ~/.codex/plugins/cache/pocketskill/my-skill ~/.claude/plugins/cache/pocketskill/my-skill -path "*/tools/wechat-search/wx_search.mjs" -print

Use the newest or source path that exists.

Workflow

  1. Identify the query, requested result count, and whether the user needs real mp.weixin.qq.com links.
  2. Run the shared tool with node.
  3. Return concise results with title, source, datetime or date_text, summary, and url.
  4. If the user asks for a file, use -o <path> and report the saved path.
  5. If real article URLs are needed, add -r; explain that URL resolution is best-effort because Sogou/WeChat may block redirect resolution.

Commands

node tools/wechat-search/wx_search.mjs "AI Agent" -n 5
node tools/wechat-search/wx_search.mjs "新能源汽车出海" -n 20 -o outputs/wx_search.json
node tools/wechat-search/wx_search.mjs "职场沟通技巧" -n 5 -r

Output Contract

The tool prints JSON:

{
  "query": "AI Agent",
  "total": 1,
  "articles": [
    {
      "title": "...",
      "url": "https://weixin.sogou.com/link?...",
      "summary": "...",
      "datetime": "2026-05-28 11:34:13",
      "date_text": "2026-05-28",
      "date_description": "4 hours ago",
      "source": "..."
    }
  ]
}

Read the full file on GitHub · 88 lines

Changes

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.

  1. 2mo ago First seen · 88 lines · 35 tokens per session scan B 10eef1b8bfee

Subscribe to this mod's changes

wechat-article-search is a skill published in the GitHub repository RongchangLi/pocketskill (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 654 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

wechat-article-search compared with skills from other repositories

wechat-article-search next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wechat-article-searchRongchangLi/pocketskillSkill23mo agoMITB35Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex