WeChat

WeChat is a skill for Claude Code from huangdijia/wechat-skills. It costs 21 tokens per session (482 once invoked), scanned A, original, MIT.

A macOS automation skill for sending text and images through the WeChat desktop app.

In plain words
What is it for?
Use it to find a contact or group and send a text message, an image, or both from a Mac.
Why use it?
It removes the need to open WeChat and navigate to a contact manually for each message.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wechat-skills plugin — 1 skill shipped together

Good fit Use it to find a contact or group and send a text message, an image, or both from a Mac.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huangdijia/wechat-skills/wechat
Install

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.

Any agent
npx skills add huangdijia/wechat-skills --skill wechat
Clone the repo
git clone --depth 1 https://github.com/huangdijia/wechat-skills

Made for: Claude Code.

Or install wechat-skills, the plugin that ships this one along with the rest of its 1 skill.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangdijia/wechat-skills/wechat"><img src="https://agentmods.dev/badge/skills/huangdijia/wechat-skills/wechat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00021 $0.00482
Opus 5 $0.00010 $0.00241
Sonnet 5 $0.00004 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured 10d ago against content hash 5587adf3a871, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

WeChat 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/wechat_send.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/wechat/SKILL.md · 76 lines

What it actually says

WeChat

macOS WeChat automation - sending messages and images via pyautogui keyboard simulation.

Features

  • Open WeChat (via Spotlight search)
  • Search for contacts/groups
  • Send text messages
  • Send images

Requirements

  • macOS system
  • Python 3.x
  • WeChat desktop app

Dependencies

pip install pyautogui pyperclip pyperclipimg

Usage

cd scripts

# Send text message
python3 wechat_send.py --name "Contact Name" --message "Message content"

# Send image
python3 wechat_send.py --name "Contact Name" --image_path="/path/to/image.png"

# Send both message and image
python3 wechat_send.py --name "Contact Name" --message "Check this out" --image_path="test.png"

Arguments

Argument Required Description
--name Yes Contact or group name
--message At least one Text message to send
--image_path At least one Path to image file

Note: At least one of --message or --image_path must be provided.

How It Works

  1. Open WeChat: Simulate Cmd+Space to open Spotlight, search for "WeChat" and launch
  2. Search contact: Simulate Cmd+F to open search, paste contact name, press Enter to enter chat
  3. Send message: Copy text to clipboard, paste and send
  4. Send image: Copy image to clipboard, paste and send

Important Notes

  • Accessibility permission is required for terminal/IDE (System Settings > Privacy & Security > Accessibility)
  • WeChat must be logged in
  • Contact name must match exactly as shown in WeChat
  • Do not operate mouse/keyboard during sending to avoid interference

File Structure

wechat-skill/
├── SKILL.md              # This documentation
├── scripts/
│   └── wechat_send.py    # Main script
Files

What ships with it

1 file 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.

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. 10d ago First seen · 76 lines · 21 tokens per session scan A 5587adf3a871

Subscribe to this mod's changes

WeChat is a skill published in the GitHub repository huangdijia/wechat-skills (11 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 482 once invoked, about $0.0001 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 2026-08-30.