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 bowlofarugula/whatsapp --skill whatsapp-messagesgit clone --depth 1 https://github.com/bowlofarugula/whatsappWrote 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/bowlofarugula/whatsapp/whatsapp-messages)<a href="https://agentmods.dev/skills/bowlofarugula/whatsapp/whatsapp-messages"><img src="https://agentmods.dev/badge/skills/bowlofarugula/whatsapp/whatsapp-messages/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/bowlofarugula/whatsapp/whatsapp-messages"><img src="https://agentmods.dev/badge/skills/bowlofarugula/whatsapp/whatsapp-messages.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 | $0.00052 | $0.00846 |
| Opus 5 | $0.00026 | $0.00423 |
| Sonnet 5 | $0.00010 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
whatsapp-messages 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/whatsapp-messages — read WhatsApp messages
Arguments passed: $ARGUMENTS (free-form, e.g. "anything new from Sam?")
Reading happens through the read_messages MCP tool (from this plugin's
WhatsApp server), with list_chats for an inbox-style overview and
search_messages for keyword lookups. read_messages returns threads
labelled Chat/Group with timestamped messages (each tagged with its
{id:…}, which you can use for react or reply_to) — any conversation,
like a mail connector reads any email. If the tools are missing or error with
not linked, run /whatsapp-setup.
The sync model (read this once)
wacli reads from a local synced store, and the read tools refresh it
first (a bounded, best-effort wacli sync). So:
- Reads are fresh to within a sync pass; the very latest message may take
a moment to appear. If a read looks like it's missing something recent, try
again, or suggest leaving
wacli sync --followrunning. - Older history that WhatsApp never pushed may simply not be in the store.
For a specific chat, deeper history can be requested from the phone with
wacli history backfill --chat <jid>(best-effort, phone must be online) — mention this only if the user is hunting for old messages.
Resolve who they mean
Names resolve against synced WhatsApp contacts/chats (wacli's local store), not an OS address book.
- A phone number or JID in the arguments → pass it straight to
read_messagesaschat. - A name → pass it as
chat(the tool resolves it), or first confirm withlist_contacts/list_chatsto be sure you've got the right person. Ambiguous or no match → ask the user for the number, or have them make sure that contact has synced (wacli contacts refresh). - No specific person ("catch me up") → call
read_messageswith nochatfor the most recently active threads (orlist_chatsfor a lighter overview). - A group ("the family group") → find it with
list_groupsorlist_chats(group rows show name + JID); pass the JID aschat.
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 · 72 lines · 52 tokens per session scan A 70653a7c34ba
whatsapp-messages is a skill published in the GitHub repository bowlofarugula/whatsapp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 846 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…