Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bowlofarugula/whatsapp/plugin install whatsappWrote 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/bowlofarugula/whatsapp/whatsapp-send)<a href="https://agentmods.dev/skills/bowlofarugula/whatsapp/whatsapp-send"><img src="https://agentmods.dev/badge/skills/bowlofarugula/whatsapp/whatsapp-send/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/bowlofarugula/whatsapp/whatsapp-send"><img src="https://agentmods.dev/badge/skills/bowlofarugula/whatsapp/whatsapp-send.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 | $0.00056 | $0.01480 |
| Opus 5 | $0.00028 | $0.00740 |
| Sonnet 5 | $0.00011 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade B, and why
whatsapp-send scanned grade B with 1 finding 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 10d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
never tell the user a dialog will review the send unless you've read 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.
/whatsapp-send — send a WhatsApp message
Arguments passed: $ARGUMENTS (free-form, e.g. "Sam let's confirm Friday"
or "+15551234567 the cut is ready")
Resolve the recipient
You need an address: a phone number in +country format
(+15551234567), a WhatsApp JID (…@s.whatsapp.net for a person,
…@g.us for a group), or a synced contact/group/chat name. wacli
resolves names and phone numbers itself, so you can usually pass what the
user said straight through as to.
- A name you're unsure about → confirm with
list_contacts(search) orlist_chatsfirst, so you address the right person. If a name is ambiguous, wacli returns multiple matches — passpick: Nto choose one. - A brand-new number with no prior chat → a phone number in
+format works directly.
Confirm, then send
Always show the exact recipient and exact message text and get a yes before sending. If the user dictated rough intent ("tell her I'm running late"), draft the text, show it, let them edit.
Send with the send_message MCP tool (this plugin's WhatsApp server):
to— phone / JID / synced name (above).text— the message, sent as written (no signature by default; see below).files— absolute paths to attach (≤100MB each); optionalcaptionon the first file.reply_to— quote a message id (the{id:…}shown byread_messages).link_preview— default true; set false to suppress the URL preview.
If the approval gate is enabled (approval: true in
~/.claude/whatsapp/config.json), the send also pauses on a client dialog
showing the recipient and final text — only the user can answer it. A
"cancelled" tool result means they declined: stop there, don't retry or
rephrase to resend. If the result says the client can't show approval
prompts, relay that message as-is — the send was blocked on purpose
(fail-closed), not broken.
The gate never replaces your in-chat confirmation. It is opt-in
config that may be off, and a dialog you assumed would appear but doesn't
means the message is already gone — that exact failure has happened. Get
the explicit yes in chat before calling send_message, every time, and
never tell the user a dialog will review the send unless you've read
~/.claude/whatsapp/config.json this session and seen approval: true.
When the gate IS on, it's the user's independent backstop on top of your
confirmation, not a substitute for it.
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.
- 10d ago First seen · 119 lines · 56 tokens per session scan B 8e1cac276311
whatsapp-send is a skill published in the GitHub repository bowlofarugula/whatsapp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,480 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…