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 dudu1111685/hermes_mcps --skill event-driven-whatsapp-watchesgit clone --depth 1 https://github.com/dudu1111685/hermes_mcpsWrote 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/dudu1111685/hermes_mcps/event-driven-whatsapp-watches)<a href="https://agentmods.dev/skills/dudu1111685/hermes_mcps/event-driven-whatsapp-watches"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/event-driven-whatsapp-watches/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/dudu1111685/hermes_mcps/event-driven-whatsapp-watches"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/event-driven-whatsapp-watches.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 | $0.01580 |
| Opus 5 | $0.00015 | $0.00790 |
| Sonnet 5 | $0.00006 | $0.00316 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
event-driven-whatsapp-watches 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Event-Driven WhatsApp Watches
Use this skill when the owner delegates a bounded WhatsApp conversation and wants Hermes to wake only when a matching incoming message arrives. This replaces frequent cron polling.
Required architecture
Hermes session calls waha_watch_chat
-> native MCP boundary injects the current Hermes origin
-> MCP stores watch + origin in a private shared store
-> MCP preserves existing WAHA config and adds listener webhook
incoming WhatsApp message
-> WAHA message + message.any webhooks
-> listener normalizes GOWS JIDs, filters/deduplicates
-> signed Hermes webhook V2 request
-> webhook route validates origin/session identity
-> gateway.wake.deliver_wake resumes exact opening session
The watch origin includes platform, chat ID/type, thread ID, user/profile/scope, durable session ID, and session key. A webhook event must not create a separate one-shot webhook conversation.
Tools
waha_send_text: sends a normal message without opening a watch.waha_send_text_and_watch: sends a text and opens the watch in one race-safe call. Prefer this when waiting for a reply, so a fast reply cannot arrive between separate send and watch calls.waha_watch_chat: opens a watch without sending any message and captures the opening Hermes session automatically.waha_list_chat_watches: reads active/closed watches without secrets.waha_update_chat_watch: changes bounded scope or expiry.waha_close_chat_watch: explicitly closes the watch when the conversation is complete. Receiving one message never closes it automatically.
Never pass _hermesOrigin manually. Hermes injects it at the native MCP boundary.
Choose exactly the simplest matching mode:
- Send only:
waha_send_textor the normal humanizedwaha_reply; no watch is created. - Send and await replies:
waha_send_text_and_watch; it creates the watch before sending and closes the new watch automatically if sending fails. - Watch only:
waha_watch_chat; no outbound WhatsApp message is sent. - Stop:
waha_close_chat_watchonce the sender appears finished and the objective is clear.
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 · 139 lines · 31 tokens per session scan A 6e1c4a756163
event-driven-whatsapp-watches is a skill published in the GitHub repository dudu1111685/hermes_mcps (5 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 1,580 once invoked, about $0.0002 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
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…