agentmods.dev

whatsapp-web-mcp AGENTS.md

whatsapp-web-mcp AGENTS.md is an instructions file for Codex, OpenCode from KingDonRush/whatsapp-web-mcp. It costs 534 tokens per session, scanned A, original, MIT.

Instructions for an agent working with WhatsApp Web through an MCP server, a program that exposes messaging tools. They define how to read chats and prepare or confirm actions without exposing browser details.

In plain words
What is it for?
Use them to check WhatsApp status, list chats, read messages, retrieve media, export chats, transcribe files, and prepare, confirm, or check the status of actions.
Why use it?
They keep the agent focused on messages and chats instead of browser controls, and help prevent accidental sending during read operations. They also require checking login status and resolving unclear chats safely.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

not rated 0 1mo ago A scan 534 tokens original MIT
View the source file KingDonRush/whatsapp-web-mcp
Install

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.

agentmods
npx agentmods add instructions/kingdonrush/whatsapp-web-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/KingDonRush/whatsapp-web-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for whatsapp-web-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kingdonrush/whatsapp-web-mcp/agents-md.svg)](https://agentmods.dev/instructions/kingdonrush/whatsapp-web-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kingdonrush/whatsapp-web-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kingdonrush/whatsapp-web-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 534 This file is loaded in full into every session.
When invoked 534 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00534 $0.00534
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 5d ago against content hash 87b88cc683df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

whatsapp-web-mcp AGENTS.md 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.

AGENTS.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WhatsApp Web MCP Agent Instructions

Public API

Use somente:

  • whatsapp_status
  • whatsapp_list_chats
  • whatsapp_get_messages
  • whatsapp_get_media
  • whatsapp_export_chat
  • whatsapp_transcribe_file
  • whatsapp_prepare_action
  • whatsapp_confirm_action
  • whatsapp_action_status

Todas as chamadas recebem um objeto request.

Domain Contract

  1. Ask for chats, messages, media, exports, transcriptions or actions as domain data. Do not manage browser sessions, selectors, scroll pages or UI state.
  2. Never use an external Playwright/browser/computer-use tool to compensate for an MCP read failure. Return the short domain error and diagnostics_id.
  3. Do not expose DOM, composer, persisted position, browser profile, Playwright or recovery mechanics to the user.
  4. Use whatsapp_status first when authentication state is unknown.
  5. Use whatsapp_list_chats to resolve ambiguity, then prefer chat_id.
  6. For recent messages, trust latest_boundary_verified; pagination uses only the opaque next_cursor.
  7. Reads never send, clear or replace user drafts.
  8. Default operation mode is headless. Set observe=true only for the current operation when the user asks to watch it.
  9. Use whatsapp_get_media with the exact chat_id and message_id. Never guess media associations.
  10. Use WhisperX only. Videos are converted to audio before transcription.
  11. Treat browser profiles, QR artifacts, exports, media and action files as sensitive.

Sending

  1. Sending requires an explicit user order.
  2. Call whatsapp_prepare_action and show its preview.
  3. Do not call whatsapp_confirm_action until the user literally confirms CONFIRMO ENVIAR <action_id>.
  4. Pass user_confirmed=true only after that confirmation.
  5. Never infer confirmation from approval of a draft, file, plan or recipient.
  6. Never retry a send automatically when its outcome is ambiguous.
  7. Text and documents, including ZIP files, are currently verified.
  8. Other media, reply and forwarding remain blocked until their own confirmed WhatsApp Web smoke passes.
  9. A successful action is consumed atomically and must not be replayed.

Read the full file on GitHub · 60 lines

Changes

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.

  1. 5d ago First seen · 60 lines · 534 tokens per session scan A 87b88cc683df

Subscribe to this mod's changes

whatsapp-web-mcp AGENTS.md is an instructions file published in the GitHub repository KingDonRush/whatsapp-web-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0027 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.

mcpplaywrightwhatsapp-webwhisperx
Related

Other instructions, from other repositories

playwright CLAUDE.md

Claude Code instructions for microsoft/playwright, covering monorepo packages, browser packages, tooling packages, key directories and build.

microsoft/playwright · 1,902 tokens

dev-browser AGENTS.md

AGENTS.md instructions for SawyerHood/dev-browser, covering repository guide, tooling and validation.

SawyerHood/dev-browser · 209 tokens

dembrandt CLAUDE.md

Claude Code instructions for dembrandt/dembrandt, covering claude.md, system instruction, development commands, running the tool and testing.

dembrandt/dembrandt · 1,311 tokens

Cobalt CLAUDE.md

Instructions for Auties00/Cobalt, covering cobalt, build, maven modules, architecture and client hierarchy.

Auties00/Cobalt · 10,056 tokens

playwright-rust CLAUDE.md

Claude Code instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.

padamson/playwright-rust · 3,446 tokens

sveltest AGENTS.md

AGENTS.md instructions for spences10/sveltest, covering agents.md, unbreakable rules, essential commands, development and testing.

spences10/sveltest · 1,850 tokens