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/triage)<a href="https://agentmods.dev/commands/rodrigopg/whatsapp-mcp/triage"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/triage/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/triage"><img src="https://agentmods.dev/badge/commands/rodrigopg/whatsapp-mcp/triage.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 | $0.00021 | $0.00799 |
| Opus 5.5 | $0.00008 | $0.00320 |
| Sonnet 5.5 | $0.00004 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
triage 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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the messages that were not reviewed yet and keep the open matters up to date. You recognize; the bridge stores and applies the fixed rules (one-month validity, when something needs attention). Nothing leaves this machine through this command: use only the tools below, never send a message.
An open matter is something agreed or asked in a one-to-one conversation that still has to happen. The owner is the user (messages with is_from_me true).
1. Fetch
Call review_next_messages (limit 100). It returns the messages, the open matters of those chats and next_cursor. Nothing moves until you call mark_reviewed.
2. Decide, message by message
Register a matter with record_matter (always citing that message) when it is:
- request: someone asks the owner for something ("me manda o contrato").
- demand: someone chases the owner about something owed ("e o orçamento?").
- promise: someone, owner included, commits to do something, with or without a date ("te mando até sexta", "vou ver e te falo").
- event: something agreed to happen ("o montador vem terça", "semana que vem a gente almoça").
Set owed_by to who has to act: owner or other.
Messages from groups only reach you when they @-mention the user, and they are addressed to the user like any other request. In a group, a matter is closed by a later message from someone else in the group confirming it.
Do not register: plain information ("o orçamento saiu hoje"), a conditional promise ("qualquer coisa eu te aviso"), pleasantries, promotions and automatic messages, unless they contain a concrete request to the owner.
- Deadline: turn "até sexta" into a date (
YYYY-MM-DD, relative to the message's own date); no time. For an event, the date it happens. No date mentioned: leave it empty. - Same subject: look at the
open_mattersof that chat first. If the message is about one of them, pass itsmatter_id(a mention) instead of creating another. - Unsure: register it with
certainty: "uncertain". The owner prefers being reminded of too much over missing something.
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 · 46 lines · 21 tokens per session scan A c3a6f6ad5a76
triage is a command published in the GitHub repository rodrigopg/whatsapp-mcp (4 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 799 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
mega-status
Show detailed status of mega-plan execution including feature progress and story completion. Usage: /plan-cascade:mega-status.
hybrid-status
Show execution status of all stories in the PRD. Displays batch progress, individual story states, completion percentage, and recent activity logs.
hybrid-complete
Complete Hybrid Ralph task in worktree, verify all stories complete, commit code changes (excluding planning files), merge to target branch, and cleanup worktree directory. Can be run from any directory.
status
Show execution status of all stories in the PRD. Displays batch progress, individual story states, completion percentage, and recent activity logs.
octo-schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.