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/sonichi/sutando/whatsappnpx skills add sonichi/sutando --skill whatsappgit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/whatsapp)<a href="https://agentmods.dev/skills/sonichi/sutando/whatsapp"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/whatsapp.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 | $0.00055 | $0.01341 |
| Opus 5 | $0.00028 | $0.00671 |
| Sonnet 5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
whatsapp 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatsApp (wacli)
Send messages, list chats, and search history using wacli — a local CLI that syncs a WhatsApp Web session into ~/.wacli/. No third-party service, no API key; the auth flow is a QR-code scan from the user's phone.
When to use
- The user asks to send a WhatsApp message, list chats, or search WhatsApp history.
- The user asks "did X message me on WhatsApp?" or similar history-search questions.
- Unpaired Mac? Probe with
wacli chats list --limit 1; if it errors "not authenticated," run the guided connect flow (python3 scripts/guided_connect.py --phone <number>) and relay its protocol lines into chat — the user never opens a terminal. Manualwacli authin a terminal is the explicit fallback only.
Install + auth
brew install openclaw/tap/wacli # one-time install (3rd-party tap, NOT Homebrew-core)
wacli auth # opens a QR for the user to scan from WhatsApp → Linked Devices
openclaw/tap is a third-party Homebrew tap (not Homebrew-core), and wacli stores a WhatsApp Web session locally at ~/.wacli/. Review the tap source before installing if security-sensitive.
The session lives at ~/.wacli/. Stays signed in across reboots until the user revokes the linked device from their phone.
Optional .env settings (label shown in WhatsApp's Linked Devices screen on the user's phone):
WACLI_DEVICE_LABEL=Sutando # any string; appears next to the device in WhatsApp → Linked Devices
WACLI_DEVICE_PLATFORM=CHROME # default per wacli is DESKTOP; CHROME is the fallback if an invalid value is set.
# See wacli's docs (https://github.com/openclaw/wacli) for the full platform-string list.
Guided connect (zero-terminal pairing)
When the user asks to connect WhatsApp, do NOT tell them to open a terminal. Run the orchestrator and relay its line protocol into the chat:
python3 skills/whatsapp/scripts/guided_connect.py --phone "+14155551234" # preferred
python3 skills/whatsapp/scripts/guided_connect.py # QR fallback
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 86 lines · 55 tokens per session scan A cee6491c5b92
whatsapp is a skill published in the GitHub repository sonichi/sutando (391 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,341 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
notifications
Send notifications through the unified notification router.
outlook
Manage Outlook email — drafting, sending, organizing, rules, vacation replies, and inbox analysis.