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 emanueleielo/ciana-parrot --skill whatsappgit clone --depth 1 https://github.com/emanueleielo/ciana-parrotWrote 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/emanueleielo/ciana-parrot/whatsapp)<a href="https://agentmods.dev/skills/emanueleielo/ciana-parrot/whatsapp"><img src="https://agentmods.dev/badge/skills/emanueleielo/ciana-parrot/whatsapp/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/emanueleielo/ciana-parrot/whatsapp"><img src="https://agentmods.dev/badge/skills/emanueleielo/ciana-parrot/whatsapp.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 | $0.00031 | $0.00852 |
| Opus 5.5 | $0.00012 | $0.00341 |
| Sonnet 5.5 | $0.00006 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the whatsapp bridge to read and send WhatsApp messages via the wacli CLI.
When to Use
- User asks to send a WhatsApp message
- Reading WhatsApp conversation history
- Searching WhatsApp chats or messages
When NOT to Use
- Telegram messages -> reply normally (Ciana routes automatically)
- iMessage/SMS -> use the
imessagebridge - Any other messaging platform
Pre-flight: Ensure Sync is Running
Before any WhatsApp operation, check that wacli is connected and syncing:
- Run
wacli-daemon statusto check if the sync daemon is running - If the status is "stopped", start it:
wacli-daemon start - After starting, wait a few seconds, then verify with
wacli doctorthat CONNECTED istrue - Only then proceed with the actual command
This ensures messages are always up-to-date without requiring the user to manually sync.
If wacli doctor shows AUTHENTICATED as false, tell the user they need to re-authenticate with wacli auth on the host (this requires scanning a QR code and cannot be done remotely).
Commands
All commands run via host_execute(bridge="whatsapp", command="...").
Sync Daemon Management
wacli-daemon status # Check if sync is running
wacli-daemon start # Start sync in background (idempotent)
wacli-daemon stop # Stop background sync
List Chats
wacli chats list --limit 20
wacli chats list --limit 20 --query "John"
Search Messages
wacli messages search "query" --limit 20
wacli messages search "query" --limit 20 --chat <jid>
wacli messages search "query" --after 2025-01-01 --before 2025-02-01
Send Text
wacli send text --to "+14155551212" --message "Hello!"
For groups, use JID format:
wacli send text --to "[email protected]" --message "Hello group!"
Send File
wacli send file --to "+14155551212" --file /path/to/image.jpg --caption "Check this"
Auth & Diagnostics
wacli auth # Interactive QR code authentication (host only)
wacli doctor # Check auth/connection/store status
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.
- 1mo ago First seen · 110 lines · 31 tokens per session scan A 4464f6643305
whatsapp is a skill published in the GitHub repository emanueleielo/ciana-parrot (77 stars, last pushed 22d ago), licensed MIT. It adds 31 tokens to every session and 852 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
skill-generator
Generates AND modifies complete skills from natural language descriptions. Guides the user through need analysis and archetype selection, produces a skill package compliant with the agentskills.io standard, and proposes it to the user, who installs it in one click. Also adjusts, enriches or fixes an existing user…
briefing-quotidien
Trigger ONLY when the user explicitly asks for a "briefing" or a complete overview of their WHOLE day. Generates the full daily briefing: agenda, tasks, weather, emails and reminders — always ALL sections together. A request about one specific category or item (appointments, meetings, events, emails, tasks, weather …
coaching-productivite
Provides productivity coaching with prioritization frameworks (Eisenhower, Pomodoro) and habit-building strategies. Use when the user asks for help organizing tasks, managing time, or improving productivity.
dice-roller
Rolls one or several dice with an animated 3D-like visual and a full breakdown of the result. Supports standard RPG notation (d4, d6, d8, d10, d12, d20, d100) and multiple dice (e.g. "2d6+3", "4d6kh3" for D&D stat rolls). Use when the user asks to roll dice, pick a random number, or decide something at random.
interactive-map
Shows an interactive Google Maps view for a given location (city, landmark, address) or for the user's own current position. Use when the user asks to show, display, or find a place on a map, or to show where they are.
qr-code
Generates a scannable QR code from text, URL, WiFi credentials or contact info. Use when the user asks for a QR code, or wants to share a link, a WiFi network, or a phone number/contact via QR.