send

A command for sending a WhatsApp message through the wu server. A JID is the internal identifier used to address a WhatsApp chat or contact.

In plain words
What is it for?
Sending a message to a supplied chat ID, chat name, contact name, or phone number, subject to the chat's access settings.
Why use it?
It can find the intended chat or contact when the user gives only a name, and it explains common connection or permission failures.

Command

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 commands/ibrahimhajjaj/wu-cli/send
Clone the repo
git clone --depth 1 https://github.com/ibrahimhajjaj/wu-cli
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00005 $0.00274
Opus 5 $0.00003 $0.00137
Sonnet 5 $0.00001 $0.00055
Haiku 4.5 $0.00001 $0.00027

Measured 2d ago against content hash 595cfabe750b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

send 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 2d 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.

claude-plugin/commands/send.md · 17 lines

What it actually says

Send a WhatsApp message using the wu MCP server.

Arguments: $ARGUMENTS

If the user provided a JID and message, send it directly. If only a message or contact name is given, first use wu_chats_search (preferred, searches by chat name) or wu_contacts_search (by contact name/phone) to find the JID, then send.

If the send fails:

  • Remote send failed: ...: wu is in remote mode and SSH or the remote daemon errored. Run /wu-status to confirm the remote daemon is reachable. The user may need to restart the remote daemon (e.g. systemctl --user restart wu on their VPS).
  • Constraint violation: ...: the chat is read-only or blocked. Tell the user to run wu config allow <jid> if they want Claude to send there.
  • Not connected to WhatsApp and no remote configured: neither a local connection nor a remote is set up. Direct them to wu login (local) or wu remote add (VPS).
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. 2d ago First seen · 17 lines · 5 tokens per session scan A 595cfabe750b

Subscribe to this mod's changes

send is a command published in the GitHub repository ibrahimhajjaj/wu-cli (14 stars, last pushed 20d ago), licensed MIT. It adds 5 tokens to every session and 274 once invoked, about $0.0000 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.