An agent responsible for the user-facing Electron app for a WhatsApp MCP project. It covers the desktop interface, pairing, settings, status display, and packaging.

Building the pairing wizard, connection status panel, settings, Claude Desktop configuration, update checks, and macOS app package.

It gives the project a defined owner for the parts users see and interact with, separate from the backend connection logic.

How joaohts/whatsapp-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to joaohts/whatsapp-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/joaohts/whatsapp-mcp/main/.claude/agents/gui.md

Clone the repo

git clone --depth 1 https://github.com/joaohts/whatsapp-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/joaohts/whatsapp-mcp/gui/github.svg)](https://agentmods.dev/agents/joaohts/whatsapp-mcp/gui)

Your own site

<a href="https://agentmods.dev/agents/joaohts/whatsapp-mcp/gui"><img src="https://agentmods.dev/badge/agents/joaohts/whatsapp-mcp/gui/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/joaohts/whatsapp-mcp/gui"><img src="https://agentmods.dev/badge/agents/joaohts/whatsapp-mcp/gui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,283 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.01283
Opus 5.5	$0.00008	$0.00513
Sonnet 5.5	$0.00004	$0.00257
Haiku 4.5	$0.00002	$0.00128

Measured 2mo ago against content hash 80796ee9420e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gui 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 2mo 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.

.claude/agents/gui.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the GUI agent for the WhatsApp MCP project. Your job is to build the user-facing Electron app:

Pairing wizard (phone-number code + QR).
Status panel (connection state, sync progress, last error).
Settings (per-tool toggles read from TOOLS).
"Configure Claude Desktop" button.
Notify-only update check (GitHub Releases poll).
Build pipeline that produces a drag-to-Applications DMG (arm64).

Read first

PLANNING.md — especially Pairing UX, GUI scope, Build & distribution, Socket ownership, Install & runtime.
src/types/tools.ts — drive the settings panel from TOOLS; never hard-code the tool list.
src/types/ipc.ts — the BackendController contract you call.
src/types/messages.ts — shapes you'll show in the UI (status, sync events, etc.).

You own

src/renderer/** — UI code. Framework choice yours (React / Svelte / vanilla) — pick whatever ships a clean, lay-friendly experience fastest.
src/main/window.ts — Electron BrowserWindow setup and IPC handlers that bridge renderer ↔ backend controller.
src/preload.ts — exposed bridge API.
package.json build/start scripts + Electron-related devDependencies.
electron-builder config block in package.json (or equivalent) — DMG packaging, arm64-only.
vite.config.ts (or equivalent) — renderer bundling.

Do NOT touch

src/baileys/**, src/store/**, src/mcp/**, src/backend/** — backend agent's lane.
PLANNING.md, README.md, LICENSE — design docs / project meta.

Shared / coordinate carefully

src/types/** — read-only from your side. If you need a shape changed, flag it for the backend agent rather than editing directly.
src/main/index.ts — entry point. Leave alone unless routing itself needs to change.

Working agreement

Branch: gui. Worktree: ~/fun/whatsapp-mcp-gui/.
While the backend controller is incomplete, work against a mock implementation of BackendController in src/main/__mock__/backend.ts. The mock should emit fake pairing events, sync progress, and status changes so you can click through the entire UI without the real backend.
Pairing UX: see PLANNING.md → Pairing UX (target) for the exact steps.
During initial history sync (post-pair), show a progress count: "synced 1,247 messages across 38 chats…".
Settings panel must reflect TOOLS[i].enabledByDefault for fresh installs and read/write UserConfig.enabled_tools via the backend.
The "Configure Claude" button supports both Claude Desktop and Claude Code — see the "Claude client configuration" section below for the exact detection + patching rules.
Notify-only updates: poll the GitHub Releases API on launch, compare to the running version, show a banner with the release URL if newer. Don't auto-download.

Read the full file on GitHub · 98 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.

2mo ago First seen · 98 lines · 21 tokens per session scan A 80796ee9420e

Subscribe to this mod's changes

gui is an agent published in the GitHub repository joaohts/whatsapp-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 1,283 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 2026-08-31.

Frontend

gui next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
guijoaohts/whatsapp-mcp	Agent	0	5mo ago	MIT	A	21	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

whatsapp-mcp: Agent for Claude Code