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 zbvxbb622-code/wechat-mcp-friend-automation --skill wechat-mcp-operatorgit clone --depth 1 https://github.com/zbvxbb622-code/wechat-mcp-friend-automationWrote 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/zbvxbb622-code/wechat-mcp-friend-automation/wechat-mcp-operator)<a href="https://agentmods.dev/skills/zbvxbb622-code/wechat-mcp-friend-automation/wechat-mcp-operator"><img src="https://agentmods.dev/badge/skills/zbvxbb622-code/wechat-mcp-friend-automation/wechat-mcp-operator/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/zbvxbb622-code/wechat-mcp-friend-automation/wechat-mcp-operator"><img src="https://agentmods.dev/badge/skills/zbvxbb622-code/wechat-mcp-friend-automation/wechat-mcp-operator.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 | $0.00086 | $0.01549 |
| Opus 5 | $0.00043 | $0.00775 |
| Sonnet 5 | $0.00017 | $0.00310 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
wechat-mcp-operator 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 9d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat MCP Operator
Core Rule
Use this skill as the operating manual for the local wechat-mcp MCP server. A skill cannot click WeChat by itself; real WeChat actions must use MCP tools or the installed wechat-followup-monitor command.
Before real actions, verify wechat-mcp is available in the current Codex task. If it is not visible, ask the user to open a new task or restart Codex so MCP tools refresh.
Available MCP Tools
read_wechat_contacts_from_excel: Read Excel rows and generate contact payloads.add_contacts_from_excel_rows: Read Excel rows and add contacts.add_contact_by_wechat_id: Add one WeChat ID directly.check_contact_status: Classify a target asadded,waiting,not_added,not_found, orunknown.fetch_messages_by_chat: Read recent messages for a contact or group.reply_to_messages_by_chat: Send a message to a contact or group.publish_moment_without_media: Publish or draft a text-only Moments post.
The repository also contains local follow-up helpers for accepted contacts, but those direct send helpers are not exposed as default MCP tools.
Default Creator Outreach Rules
- Nickname column:
B - Xiaohongshu ID column:
C - WeChat ID column:
AZ - First data row:
3 - Default batch add-friend delay:
10seconds between contacts - Cooldown after every
20contacts: wait10minutes - Friend request text:
你好，想和你沟通商务合作 - Remark format:
小红书-{nickname}-{redbook_id} - Contact search/open target: use
wechat_idfirst;remarkis only for friend-request notes and records. - Follow-up message after acceptance:
你好，想和你进一步沟通商务合作，方便时请回复这条消息 - Shared follow-up image: pass the same QR image once with
followup_image_path. - Privacy default:
all - Hide my posts:
false - Hide their posts:
false
Use rows for exact row selection, such as 3, 3,5,8, 3-6, or 3,5-8.
Stage Boundaries
- Real add-friend flow must not assume the contact is accepted; there is no default-pass mode.
- Add-friend actions must use WeChat UI buttons/clicks for
添加到通讯录, request submission, notes, and confirmation. Do not use Enter as a substitute for add-friend buttons. - Chat/message actions may use Enter after the accepted contact chat is opened: search by
wechat_id, press Enter into the chat, paste the message, then press Enter to send.
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.
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.
- 9d ago First seen · 119 lines · 86 tokens per session scan A 32b3db0383e1
wechat-mcp-operator is a skill published in the GitHub repository zbvxbb622-code/wechat-mcp-friend-automation (0 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,549 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
openclaw-rpa
Record browser, Excel, Word & API actions once — replay without the LLM: faster, cheaper, no hallucinations. github.com/laziobird/openclaw-rpa . Supports computer-use automation: web clicks/fill/extract, local Excel (.xlsx via openpyxl), Word (.docx via python-docx), HTTP API calls (httpx GET/POST), and auto-login…
browser-data-scraper
Scrapes structured data from static web pages into JSONL and exports to CSV, XLSX, or JSONL. Use when asked to 'scrape a website', 'extract data from these URLs', 'collect listings into a spreadsheet', 'paginate through search results', 'crawl a sitemap', or 'pull records from a page'. Handles URL-parameter…
table-to-csv
Converts visible web tables — HTML tables, pricing grids, comparison charts, reports — into clean Markdown tables that users can copy or download as CSV from the extension. Use when the user wants to extract, scrape, convert, copy, or export a table from a webpage.
excel-webview2-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Excel WebView2 via CLI.
excel-webview2
Uses Excel WebView2 via MCP to debug, inspect, and automate an Excel add-in's embedded WebView2 browser. Use when inspecting or interacting with a running Excel add-in's task pane or web content. Requires the add-in to already be running with remote debugging enabled on port 9222.
court-auction-scraper
A browser-automation skill for searching South Korean court-auction listings on courtauction.go.kr and organising results in an Excel file.