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.
git clone --depth 1 https://github.com/rodrigopg/whatsapp-mcpWrote 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/commands/rodrigopg/whatsapp-mcp/style)<a href="https://agentmods.dev/commands/rodrigopg/whatsapp-mcp/style"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/style.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00901 |
| Opus 5 | $0.00010 | $0.00451 |
| Sonnet 5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
style 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 8d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a writing-style profile from the user's own sent WhatsApp messages, so future drafted/sent messages match how they actually write — not a generic AI tone.
1. Scope the sample
If more than one whatsapp* MCP server is configured (see ~/.claude.json), ask which account to learn from.
Ask with AskUserQuestion: "Which chats should I learn from?" — options like "A specific chat" (then ask for it) / "General — sample across recent chats" / "Skip a chat I name" (for cases where one contact's tone shouldn't count, e.g. a work channel with a very different register than personal chats).
Also ask sample size loosely: "How many of your own messages should I read? (more = more accurate, slower)" — default suggestion 150-300 if the user has no preference.
2. Pull messages
Use list_messages (via the resolved mcp__<server>__list_messages tool) with include_context: false to keep the read light. If scoped to one chat, pass chat_jid. If general, use a large limit per page (e.g. 100) rather than the tool's small default — small pages mean many round trips before enough From: Me: lines accumulate.
Each returned line is formatted [timestamp] Chat: X From: Y: content. Keep only lines where the sender is the user (From: Me: — matches how format_message in this codebase marks the user's own messages). Discard everyone else's lines; they're context, not signal.
Discard every line from status@broadcast outright, general sample or not — it's WhatsApp's status/stories feed, not a conversation, and it can dominate a general sample by sheer volume (contact status updates land there constantly) while carrying zero conversational-style signal. If a general sample is heavy on it and light on real "From: Me:" lines, that's the signal to keep paging rather than assume the account has little to learn from.
Skip media placeholders ([image - ...], [audio - ...]) and near-empty messages (single-word acks, reaction-forwards) — they don't carry style. Keep the actual sentences.
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.
- 8d ago First seen · 44 lines · 19 tokens per session scan A 425658975f9c
style is a command published in the GitHub repository rodrigopg/whatsapp-mcp (2 stars, last pushed 12d ago), licensed MIT. It adds 19 tokens to every session and 901 once invoked, about $0.0001 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 commands, from other repositories
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
typegen
Run Sanity TypeGen and troubleshoot type generation issues.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
review-epo-formalities
Check patent application formalities for EPO compliance (Rules 42-49 EPC, EPO Guidelines Part A).
full-review
Complete patent application review (claims + specification + formalities in parallel).
review-formalities
Check patent application formalities (abstract, title, drawings per MPEP 608).