wechat-send-file

wechat-send-file is a skill for Claude Code from cookjohn/teammcp. It costs 35 tokens per session (580 once invoked), scanned B, original, MIT.

A skill that sends a local file, image, or document to WeChat through a connected bridge. WeChat is a messaging app.

In plain words
What is it for?
Use it when you need to send a file path to WeChat and confirm whether the transfer succeeded.
Why use it?
It handles checking the file and connection before sending, so you do not have to call the messaging service manually.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the fakechat plugin — 9 skills shipped together

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.

agentmods
npx agentmods add skills/cookjohn/teammcp/wechat-send-file
Any agent
npx skills add cookjohn/teammcp --skill wechat-send-file
Clone the repo
git clone --depth 1 https://github.com/cookjohn/teammcp

Made for: Claude Code.

Or install fakechat, the plugin that ships this one along with the rest of its 9 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-send-file

README.md
[![agentmods](https://agentmods.dev/badge/skills/cookjohn/teammcp/wechat-send-file.svg)](https://agentmods.dev/skills/cookjohn/teammcp/wechat-send-file)
Your own site
<a href="https://agentmods.dev/skills/cookjohn/teammcp/wechat-send-file"><img src="https://agentmods.dev/badge/skills/cookjohn/teammcp/wechat-send-file.svg" alt="Measured on agentmods" 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 580 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00580
Opus 5 $0.00017 $0.00290
Sonnet 5 $0.00007 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 6d ago against content hash 415ced712ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

wechat-send-file scanned grade B with 2 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 6d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

fetch('http://localhost:3100/api/wechat/send-file', { method: 'POST',

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3100/api/wechat/status -H "Authorization: Bearer $TEAMMCP_KEY"
plugin-dist/templates/skills/wechat-send-file/SKILL.md · 79 lines

What it actually says

Send File to WeChat

Send a local file (image, document, video) to WeChat via the TeamMCP WeChat bridge.

Arguments

$ARGUMENTS contains the file path to send. If not provided, ask the user which file to send.

Steps

1. Validate File

Check the file exists and get its size:

Use the Bash tool to run: ls -la "$ARGUMENTS"

If the file doesn't exist, tell the user and ask for a correct path.

2. Check WeChat Connection

Call the TeamMCP API to verify WeChat is connected:

Use the Bash tool to run:
curl -s http://localhost:3100/api/wechat/status -H "Authorization: Bearer $TEAMMCP_KEY"

If connected is false, tell the user to connect WeChat first via the Dashboard.

3. Send File

Call the send-file API:

Use the Bash tool to run:
node -e "
fetch('http://localhost:3100/api/wechat/send-file', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json', 'Authorization': 'Bearer $TEAMMCP_KEY' },
  body: JSON.stringify({ file_path: '$ARGUMENTS' })
}).then(r=>r.json()).then(d => {
  if (d.ok) console.log('File sent:', d.fileName, '(' + d.size + ' bytes)');
  else console.error('Failed:', d.error);
});
"

4. Report Result

Tell the user whether the file was sent successfully, including the filename and size.

Supported File Types

Type Extensions WeChat Display
Image jpg, jpeg, png, gif, bmp, webp Inline image
Video mp4, avi, mov, wmv, mkv Video player
File All others (pdf, doc, md, txt, etc.) File attachment

How It Works

  1. File is encrypted with AES-128-ECB (random key)
  2. Encrypted data is uploaded to WeChat CDN via getuploadurl + POST
  3. CDN returns a download parameter
  4. sendmessage sends the media reference to the WeChat user

Prerequisites

  • WeChat bridge must be connected (scan QR code via Dashboard)
  • A recent WeChat message from the user is needed (provides context_token, valid 24h)
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. 6d ago First seen · 79 lines · 35 tokens per session scan B 415ced712ca6

Subscribe to this mod's changes

wechat-send-file is a skill published in the GitHub repository cookjohn/teammcp (53 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 580 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.