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/favorites)<a href="https://agentmods.dev/commands/rodrigopg/whatsapp-mcp/favorites"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/favorites/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/commands/rodrigopg/whatsapp-mcp/favorites"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/favorites.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 | $0.00014 | $0.00319 |
| Opus 5.5 | $0.00006 | $0.00128 |
| Sonnet 5.5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
favorites 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 5d 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.
What it actually says
Help the user build the list of favorites that comes first in their summaries. A favorite is the WhatsApp Favorites list; if it is empty (or incomplete), suggest names from how the user actually talks. You only propose: every name becomes a favorite by the user's own decision. Nothing leaves this machine and no message is sent.
1. Look at what exists
Call list_favorites (an empty list is normal) and show it.
2. Suggest
Call suggest_favorites. It returns one-to-one chats of the last month with real two-way traffic (someone who only writes to the user, like a shop or a promotion, is never proposed), with how many messages came from each side. Show one table: name, messages from them, messages from the user.
3. Decide, one name at a time
Ask the user about each suggested name: keep as favorite, not a favorite, or skip for now. Record only what they answer with decide_favorite:
accept: becomes a favorite.reject: never suggested again.remove: forget an earlier decision.
Do not decide for the user, not even for names that look obvious. A name they skip is not recorded.
4. Finish
Call list_favorites and show the result. Tell them they can also mark favorites in WhatsApp itself: that list is read by the bridge when WhatsApp syncs it.
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.
- 5d ago First seen · 28 lines · 14 tokens per session scan A 47f0ac42612a
favorites is a command published in the GitHub repository rodrigopg/whatsapp-mcp (4 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 319 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.
Other commands, from other repositories
backfill
Backfill older message history.
messages
List messages in a WhatsApp chat.
context
Get surrounding message context.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.
implement
Multi-agent advisory squad workflow for implementing code changes: classify → score risk → select agents → planner → Gate 1 (plan approval) → advisory squad → Gate 2 (Blocker halt) → implementer → consolidator → verdict. Auto-detects depth (quick/normal/deep) from risk + file count; pass --quick or --deep to override.…
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.