Borrowing it
Nothing to install: this file belongs to Sealjay/mcp-whatsapp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Sealjay/mcp-whatsapp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Sealjay/mcp-whatsappWrote 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/instructions/sealjay/mcp-whatsapp/claude-md)<a href="https://agentmods.dev/instructions/sealjay/mcp-whatsapp/claude-md"><img src="https://agentmods.dev/badge/instructions/sealjay/mcp-whatsapp/claude-md/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/instructions/sealjay/mcp-whatsapp/claude-md"><img src="https://agentmods.dev/badge/instructions/sealjay/mcp-whatsapp/claude-md.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 | $0.01687 | $0.01687 |
| Opus 5.5 | $0.00675 | $0.00675 |
| Sonnet 5.5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
mcp-whatsapp CLAUDE.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 21d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Single Go binary that runs as an HTTP MCP daemon (default 127.0.0.1:8765) wrapping whatsmeow to expose a personal WhatsApp account as MCP tools. whatsapp-mcp serve is the long-running process: it tracks WhatsApp events, caches messages locally, serves MCP at /mcp, and hosts the pairing UI at /pair. MCP clients connect over stateless Streamable HTTP (server.WithStateLess(true); MCP 2026-07-28 and older revisions, no Mcp-Session-Id).
Structure
cmd/whatsapp-mcp/ login, serve, smoke subcommands
internal/client/ whatsmeow client wrapper (send, download, events, history, features)
internal/daemon/ HTTP server, pairing state machine, /pair endpoint
internal/mcp/ mark3labs/mcp-go v1 server + tool registrations
internal/media/ ogg analysis + ffmpeg shell-out
internal/security/ path allowlisting, filename sanitisation, log redaction
internal/store/ SQLite cache + queries + LID resolution + formatters
scripts/mdtest-parity.sh whatsmeow API drift canary
Data lives under ./store/ (override with -store DIR): messages.db, whatsapp.db (session) and .lock. To force a re-sync, delete both databases and re-run login. Binary is bin/whatsapp-mcp.
Subcommands
login— pair the device via QR (or-phonefor a pairing code), write session tostore/whatsapp.db.serve— HTTP daemon on127.0.0.1:<port>; tracks events + serves MCP at/mcp; pairing UI at/pair. Holdsstore/.lockwhile running and is mutually exclusive with any otherserveinstance using the same store directory.smoke— boot-test without connecting to WhatsApp.
Testing
make test # unit tests
make test-race # with -race
make e2e # spawn the binary, speak JSON-RPC over HTTP (both MCP eras; fails if a session ID is minted)
make smoke # boot-test without connecting to WhatsApp
make vet # go vet
Fixtures: internal/store/testdata/seed.sql seeds three chats + ~12 messages with a mix of direct/group, media, is_from_me, and LID-originated variants. Used by store tests via openTestStore(t) in internal/store/testutil_test.go.
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.
- 21d ago Changed · -7 lines · +242 tokens per session 3699d9ecc866
- 2mo ago First seen · 82 lines · 1,445 tokens per session scan A 3ccc11de5105
mcp-whatsapp CLAUDE.md is an instructions file published in the GitHub repository Sealjay/mcp-whatsapp (18 stars, last pushed 20d ago), licensed MIT. It adds 1,687 tokens to every session, about $0.0067 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.
mcp-whatsapp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-whatsapp CLAUDE.mdSealjay/mcp-whatsapp | Instructions file | 18 | 20d ago | MIT | A | 1,687 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |