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 bowlofarugula/whatsapp --skill whatsapp-listengit clone --depth 1 https://github.com/bowlofarugula/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-listen)<a href="https://agentmods.dev/skills/bowlofarugula/whatsapp/whatsapp-listen"><img src="https://agentmods.dev/badge/skills/bowlofarugula/whatsapp/whatsapp-listen/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-listen"><img src="https://agentmods.dev/badge/skills/bowlofarugula/whatsapp/whatsapp-listen.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 | $0.00098 | $0.00962 |
| Opus 5 | $0.00049 | $0.00481 |
| Sonnet 5 | $0.00020 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
whatsapp-listen 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 11d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/whatsapp-listen — watch a thread for new messages
Arguments passed: $ARGUMENTS (e.g. "alex", "sam until she confirms")
This is a session-bound listener: it works only while this session is open and the machine is awake. Say so up front in one line when starting. For true 24/7 unattended response, this is the wrong tool — see docs/AUTOREPLY.md and its tradeoffs (including the raised WhatsApp-ban risk of unattended sending).
Start
- Resolve the contact (
list_contacts/list_chats→ ask). Note their JID — addressing by JID is the most reliable across polls. - Establish a baseline:
read_messagesfor that chat; note the timestamp and content of the latest message. Report the baseline to the user. - Ask (or infer from the request) what to do on arrival: just notify, or notify + draft a reply for approval.
Poll loop
For long-running, across-turn monitoring this skill polls with ScheduleWakeup
(below) — that's the primary loop, because it doesn't hold a turn open. The
watch MCP tool is the other option: it blocks up to ~60s polling the synced
store for the next message and is the right pick only for a short, active
wait inside one turn ("hold on for her reply"), not for monitoring that should
span minutes or hours. Pass the cursor (a timestamp) it returns back as
since to avoid missing anything between waits.
Both paths rely on the local store being fresh. read_messages and watch
auto-sync before they read, so you don't need to manage sync — but for tight,
responsive watching the user can also leave wacli sync --follow running in a
terminal to keep the store continuously warm.
Schedule a wakeup (ScheduleWakeup) carrying a self-contained prompt: contact name, JID, baseline timestamp, and the on-arrival behavior. Cadence:
- Actively waiting on a specific reply ("tell me when she confirms") → ~270s, staying inside the prompt-cache window.
- Casual monitoring ("keep an eye on the thread") → 1200–1800s; don't burn a cache miss every 5 minutes for a thread that moves hourly.
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.
- 11d ago First seen · 78 lines · 98 tokens per session scan A 0028187bd01d
whatsapp-listen is a skill published in the GitHub repository bowlofarugula/whatsapp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 98 tokens to every session and 962 once invoked, about $0.0005 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
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.