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 sanjay3290/ai-skills --skill whatsappgit clone --depth 1 https://github.com/sanjay3290/ai-skillsWrote 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/sanjay3290/ai-skills/whatsapp)<a href="https://agentmods.dev/skills/sanjay3290/ai-skills/whatsapp"><img src="https://agentmods.dev/badge/skills/sanjay3290/ai-skills/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/sanjay3290/ai-skills/whatsapp"><img src="https://agentmods.dev/badge/skills/sanjay3290/ai-skills/whatsapp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.01104 |
| Opus 5 | $0.00064 | $0.00552 |
| Sonnet 5 | $0.00026 | $0.00221 |
| Haiku 4.5 | $0.00013 | $0.00110 |
Grade A, and why
whatsapp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatsApp (pywhats)
Drive a WhatsApp account as a linked companion device (like WhatsApp Web)
from async Python via pywhats (pre-alpha,
text/image only). This is an unofficial multi-device client — not the
official WhatsApp Business / Cloud API.
CLI entrypoint: scripts/wa.py (auto-bootstraps a managed venv on first run).
Mental model
- Pairing = one-time QR scan.
wa.py pairshows an ASCII QR; scan it in WhatsApp → Linked Devices. Credentials persist to$PYWHATS_HOME/<session>.session(+.signal.db). - Resuming = silent. Later commands reconnect with the same session — no QR.
- JIDs address chats. Bare phone
15550001234→[email protected]; groups use[email protected]. - Events are how you receive.
wa.py listenprints one JSON object per event.
⚠️ Never bare-await Client calls inside a handler
Event handlers run inline on the receive loop. Awaiting send_*,
mark_read, get_group_info, download_media, etc. inside a handler
deadlocks the connection. Always asyncio.create_task(...). The listen
subcommand already does this for --read.
Commands
scripts/wa.py pair # one-time QR pair
scripts/wa.py send-text 15550001234 "hello" # 1:1 text
scripts/wa.py send-image 15550001234 photo.jpg --caption hi # 1:1 image
scripts/wa.py group-info [email protected] # group metadata JSON
scripts/wa.py group-send [email protected] "hi all" # group text
scripts/wa.py mark-read 15550001234 MSGID [--sender JID] # blue ticks
scripts/wa.py presence available # global presence
scripts/wa.py typing 15550001234 composing [--media audio] # typing indicator
scripts/wa.py listen --read --events message,receipt # JSONL event stream
scripts/wa.py --session work send-text 15550001234 "hi" # named session
| Command | Behavior |
|---|---|
pair |
Fresh link via ASCII QR; idempotent if already paired |
send-text <to> <text> |
Send 1:1 text; print message id |
send-image <to> <path> [--caption C] |
Send image (jpg/png/webp, ≤16MB); print id |
group-info <gid> |
Print group JSON (subject, owner, participants, …) |
group-send <gid> <text> |
Resolve members then send group text; print id |
mark-read <chat> <ids...> |
Blue-tick; --sender for groups |
presence <available|unavailable> |
Global presence |
typing <to> <composing|paused> |
Chat presence; optional --media audio |
listen |
Long-running JSON lines; --read, --events, --subscribe JID (required for presence events) |
What ships with it
4 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.
- 11d ago First seen · 84 lines · 129 tokens per session scan A ad01b6d7699b
whatsapp is a skill published in the GitHub repository sanjay3290/ai-skills (422 stars, last pushed today), licensed Apache-2.0. It adds 129 tokens to every session and 1,104 once invoked, about $0.0006 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.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
neo-sub-agent
Use this skill when the user asks to design, create, review, or convert sub-agents, custom agents, worker/reviewer/planner agents, background agents, or multi-agent workflows for Antigravity CLI, Codex, Claude Code, GitHub Copilot CLI, or neutral agent blueprints.
diaoding-zhuangxiu-zhinan
A Chinese-language knowledge guide about ceiling renovations, including materials, construction methods, room height, and ceiling designs.
pr-walkthrough
Generate a static interactive D3 walkthrough of a pull request. Use when the user wants a zoomable PR map, graph/canvas PR orientation, or alternate visualization of PR system components, data flow, code dependencies, and user actions.
dengguang-zhaoming-bikeng-zhinan
A Chinese-language knowledge guide about home lighting, including ceiling lights, light strips, color temperature, color rendering, and room zoning.
igce-builder-ffp
Trigger for: FFP IGCE, firm-fixed-price estimate, FFP cost model, proposed FFP rate validation, wrap-rate analysis, Agency BPA rate comparison, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable Firm-Fixed-Price federal estimates using BLS OEWS wages, layered fringe/overhead/G&A/profit, GSA…