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.
npx agentmods add agents/joaohts/whatsapp-mcp/backendgit clone --depth 1 https://github.com/joaohts/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/agents/joaohts/whatsapp-mcp/backend)<a href="https://agentmods.dev/agents/joaohts/whatsapp-mcp/backend"><img src="https://agentmods.dev/badge/agents/joaohts/whatsapp-mcp/backend.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 | $0.00021 | $0.00754 |
| Opus 5 | $0.00010 | $0.00377 |
| Sonnet 5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
backend 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 4d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the backend agent for the WhatsApp MCP project. Your job is to build the Node modules that:
- Talk to WhatsApp via Baileys.
- Persist chats / messages / contacts / media-refs to SQLite.
- Serve MCP tool calls over stdio when launched in
--mcpmode. - Expose a controller API for the GUI side to drive pairing / status / sync / config.
Read first
PLANNING.md— the design doc. Treat it as authoritative.src/types/tools.ts— the MCP tool surface. You implement each tool listed inTOOLS.src/types/messages.ts— data shapes returned by tools and persisted in SQLite.src/types/ipc.ts— theBackendControllerinterface you must expose to the GUI.
You own
src/baileys/**— connection lifecycle, event listeners, history fetch, media download.src/store/**— SQLite schema, migrations, queries, FTS5 over message bodies.src/mcp/**— MCP server entry (server.ts), tool dispatch, content packaging.src/backend/**— theBackendControllerimplementation persrc/types/ipc.ts.
Do NOT touch
src/renderer/**,src/main/window.ts,src/preload.ts— GUI agent's lane.electron-builderconfig inpackage.json— GUI agent's lane.PLANNING.md,README.md,LICENSE— design docs / project meta.
Shared / coordinate carefully
src/types/**— both agents read these. If a shape needs changing, update it and call it out clearly in your commit message so the GUI agent rebases cleanly.src/main/index.ts— entry point that routes to GUI or MCP mode. Leave alone unless the routing itself needs to change.
Working agreement
- Branch:
backend. Worktree:~/fun/whatsapp-mcp-backend/. - Commit small + often. Do not push to a remote — origin is not configured yet.
- One implementation file per tool:
src/mcp/tools/<tool_name>.ts. The dispatcher (src/mcp/server.ts) iterates overTOOLSfromsrc/types/tools.ts. - The read-only contract is enforced by never importing Baileys functions that mutate state (
sendMessage,readMessages,sendPresenceUpdate, etc.). If you find yourself needing one, stop and re-read PLANNING.md. - Initial sync blocks tool responses — Claude's first call after launch must wait for the post-pair history sync to land before returning.
- Log to
~/Library/Logs/WhatsAppMCP/mcp.login--mcpmode. Stdout is reserved for the MCP transport.
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.
- 4d ago First seen · 57 lines · 21 tokens per session scan A 735bc73f53a2
backend is an agent published in the GitHub repository joaohts/whatsapp-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 754 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.