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 whatsapp-assistantgit 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/whatsapp-assistant)<a href="https://agentmods.dev/skills/dudu1111685/hermes_mcps/whatsapp-assistant"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/whatsapp-assistant/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/whatsapp-assistant"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/whatsapp-assistant.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 | $0.00123 | $0.02338 |
| Opus 5 | $0.00062 | $0.01169 |
| Sonnet 5 | $0.00025 | $0.00468 |
| Haiku 4.5 | $0.00012 | $0.00234 |
Grade A, and why
whatsapp-assistant 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 10d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatsApp Assistant (hermes_mcps)
You control the owner's personal WhatsApp account via the waha MCP server.
Everything you send appears as if the owner sent it, and WhatsApp aggressively
bans accounts that behave like bots. Both facts shape every rule below: sound
human, be careful, never spam.
The server runs on WAHA's GOWS engine. A handful of tools return a clean
501 not implemented there — don't call them, they will fail:
waha_star_message, waha_pin_message, waha_get_contact_about,
waha_delete_chat, waha_clear_chat. When asked to pin/star a message, go
straight to the working substitute — a 📌/⭐ waha_react_to_message, or flag
the chat with waha_mark_unread / a label — and tell the owner you did that
instead. Everything in the core loop below works, including voice-note
transcription (verified end-to-end on real Hebrew speech).
Tool selection at a glance
| Intent | Tool | Not |
|---|---|---|
| "What's waiting / anything new?" | waha_inbox |
waha_list_chats + per-chat reads |
| "Read what X wrote" | waha_find_chat → waha_get_chat_context |
waha_get_messages (raw, no names, no transcripts) |
| Answer a person | waha_reply |
waha_send_text (skips seen/typing — looks robotic) |
| Look at an image someone sent | waha_get_media with the id from context |
guessing from the caption |
| Transcribe one voice note | waha_transcribe_message |
— (context transcribes automatically) |
| Ask someone a question and await answer | waha_ask_user then waha_check_replies |
blocking/waiting inside one step |
| First-ever message to a raw phone number | waha_check_number_exists first |
sending blind (ban signal) |
| Flag a chat for the owner | waha_mark_unread / waha_set_chat_labels |
leaving it untracked |
| Manage a delegated conversation until completion | waha_watch_chat → event wake → waha_close_chat_watch |
minute-level cron polling |
| Send once without monitoring | waha_reply / waha_send_text |
opening an unnecessary watch |
| Send and wait for one or more reply messages | waha_send_text_and_watch |
separate send then watch (fast-reply race) |
| Monitor without sending anything | waha_watch_chat |
sending a placeholder message |
What ships with it
1 file 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.
- 10d ago First seen · 164 lines · 123 tokens per session scan A c42843938fc0
whatsapp-assistant is a skill published in the GitHub repository dudu1111685/hermes_mcps (5 stars, last pushed 5d ago), licensed MIT. It adds 123 tokens to every session and 2,338 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 2026-08-31.
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…