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 agentmods add skills/cookjohn/teammcp/wechat-send-filenpx skills add cookjohn/teammcp --skill wechat-send-filegit clone --depth 1 https://github.com/cookjohn/teammcpWrote 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/cookjohn/teammcp/wechat-send-file)<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>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 | $0.00035 | $0.00580 |
| Opus 5 | $0.00017 | $0.00290 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
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" 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
- File is encrypted with AES-128-ECB (random key)
- Encrypted data is uploaded to WeChat CDN via
getuploadurl+ POST - CDN returns a download parameter
sendmessagesends 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)
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.
- 6d ago First seen · 79 lines · 35 tokens per session scan B 415ced712ca6
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.