A Windows-only assistant for reading recent WeChat messages and sending text messages through the logged-in WeChat PC client. It works with individual contacts and group chats.

Use it to fetch recent messages with senders, timestamps, and content, or send a text to a contact or group. It requires Windows 10 or 11, WeChat for PC, and a logged-in account.

It lets you retrieve or send messages through an AI chat instead of manually navigating WeChat for each request.

goodqunbot — Skill for Claude Code and Codex by ImGoodBai/goodable

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 ImGoodBai/goodable --skill goodqunbot

Clone the repo

git clone --depth 1 https://github.com/ImGoodBai/goodable

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/imgoodbai/goodable/goodqunbot/github.svg)](https://agentmods.dev/skills/imgoodbai/goodable/goodqunbot)

Your own site

<a href="https://agentmods.dev/skills/imgoodbai/goodable/goodqunbot"><img src="https://agentmods.dev/badge/skills/imgoodbai/goodable/goodqunbot/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/imgoodbai/goodable/goodqunbot"><img src="https://agentmods.dev/badge/skills/imgoodbai/goodable/goodqunbot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,802 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.01802
Opus 5.5	$0.00016	$0.00721
Sonnet 5.5	$0.00008	$0.00360
Haiku 4.5	$0.00004	$0.00180

Measured 2mo ago against content hash c54e835f8681, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goodqunbot 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.

The scan reads SKILL.md. This mod also ships 11 executable files (app/__init__.py, app/database.py, app/main.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/goodqunbot/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

微信消息助手 (WeChat Message Assistant)

This skill enables AI to interact with WeChat directly through AI chat, providing two core capabilities: retrieving recent messages and sending messages to contacts or groups.

Platform Requirements

OS: Windows 10/11 only
WeChat: WeChat PC client must be installed, running, and logged in
Python: Python 3.11+ (automatically handled by Goodable)

Core Capabilities

1. Retrieve Recent Messages

Fetch the last 10-15 messages from any WeChat contact or group chat.

What you can ask:

Get the last 15 messages from "张三"
Show me recent messages from "Product Team" group
Retrieve messages from "李四", last 10 only

What AI will do:

Opens the specified chat in WeChat
Retrieves the requested number of messages (default: 15, max: 100)
Returns messages with timestamp, sender, and content
Formats as structured JSON for easy parsing

2. Send Messages

Send a text message to any WeChat contact or group chat.

What you can ask:

Send "Meeting at 3pm" to "张三"
Message "Product Team" group: "Release notes updated"
Tell "李四": "Please review the document"

What AI will do:

Opens the specified chat in WeChat
Sends the message content
Confirms successful delivery

How to Use

Prerequisites

Before using this skill, ensure:

WeChat PC client is running
You are logged into your WeChat account
The contact/group name you specify exists in your WeChat

Example Usage

Scenario 1: Check messages from a colleague

User: "帮我看一下张三最近给我发了什么消息"
AI: [Runs get_messages.py script]
AI: "张三最近的5条消息：
1. [2024-01-28 10:30] 张三: 会议资料已发送
2. [2024-01-28 11:00] 张三: 请查收
..."

Scenario 2: Send a message

User: "给产品群发个消息：今天下午3点开会"
AI: [Runs send_message.py script]
AI: "消息已成功发送到产品群"

Instructions for AI

When the user requests WeChat message operations:

1. Retrieve Messages

Run the get_messages.py script:

python scripts/get_messages.py "<Contact/Group Name>" [count]

Read the full file on GitHub · 239 lines

Files

What ships with it

20 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.

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.

2mo ago First seen · 239 lines · 41 tokens per session scan A c54e835f8681

Subscribe to this mod's changes

goodqunbot is a skill published in the GitHub repository ImGoodBai/goodable (196 stars, last pushed 9mo ago), licensed MIT. It adds 41 tokens to every session and 1,802 once invoked, about $0.0002 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 2026-08-30.

Productivity base44 claudeagentsdk claudecode codeagent lovable vibecoding

pi-agent

Builds with and operates Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment variables, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, running local…

K-Dense-AI/scientific-agent-skills · 119 tokens

trellis-channel

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

mindfold-ai/Trellis · 32 tokens

herdr-names

Rename Herdr tabs, panes, and agents so each sidebar entry says in a few words what that session is doing. Use whenever the user mentions Herdr and wants tab, pane, or agent names renamed, relabeled, cleaned up, tidied, or made clearer; says a tab or agent name is confusing, meaningless, stale, or just a number; asks…

petekp/claude-code-setup · 167 tokens

goodqunbot