Borrowing it
Nothing to install: this file belongs to HalemoGPA/whatsapp-mcp-server. 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/HalemoGPA/whatsapp-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/HalemoGPA/whatsapp-mcp-serverWrote 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/halemogpa/whatsapp-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/halemogpa/whatsapp-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/halemogpa/whatsapp-mcp-server/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/halemogpa/whatsapp-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/halemogpa/whatsapp-mcp-server/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 | $0.02392 | $0.02392 |
| Opus 5 | $0.01196 | $0.01196 |
| Sonnet 5 | $0.00478 | $0.00478 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
whatsapp-mcp-server 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 8d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo
Read this before changing anything. It is short on purpose.
The one idea
WhatsApp enforces almost everything client-side. The display is not the truth.
"View once", "delete for everyone", poll selection caps, forwarding labels - these are conventions maintained by the app's UI, not guarantees enforced by WhatsApp's servers. The app bets that what people see IS reality, and for almost everyone that bet is correct. It is not correct for us: we read the wire.
The practical consequence, which cost a full day on 2026-07-16:
A rendering is evidence of what a client chose to draw. Nothing more.
Every wrong conclusion that day came from trusting something that renders:
| Trusted | Said | Truth |
|---|---|---|
| WhatsApp Desktop | "only once - view from your phone" | The message was NOT view-once. Desktop reads the envelope; mobile enforces the inner viewOnce flag, which was unset. Fake view-once for weeks. |
| A code comment | "media bytes are downloadable regardless of view count" | True when written (Aug 2024), false since Meta's server-side fix (~Nov 2024). Repeated as fact without checking. |
| whatsmeow's docs | selectableOptionCount is "the maximum number of selections" |
No client enforces N>1. Library docs describe the field's intent, not client behaviour. |
| Our own docstring | "single-select polls will ignore extras" | They do not. 3 options on a cap-2 poll register all 3. |
| A poll tally in the app | option counts | Five phones showed five different tallies (1/3/3 vs 2/3/2) while the wire said 5/5/5. |
The wire never lied. Every single time, the fix was to go look at the actual protobuf, the actual stanza, or run an actual test.
Rules that follow from it
- Cite the wire, the proto field number, or a test you ran. Not a doc, not a comment, not a screenshot. If you cannot, say "unverified" and mean it.
- A proto field existing does not mean it works. The server may reject it and
the recipient's client may ignore it. Those are three different claims. Keep
them separate. See
docs/protocol-vs-app.md. - Never repeat a comment in this repo as fact. They rot. The two most confidently wrong statements of 2026-07-16 were both comments in this codebase that had been true when written.
- Do not claim it works until you have watched it work. "Compiles",
"deployed", and "the endpoint returned success" are not "works". A poll vote
returned
Vote castwhile the tally silently stayed at 0. - Phone-origin bugs are invisible to MCP-side testing. Sending through our own API exercises code that hashes/wraps locally and never decrypts or normalises. Two real bugs (all six poll-creation variants; LID-vs-PN on votes) were found within minutes by the user's phone after our own tests passed clean. Close the loop with a real phone before claiming a receive path works.
- When the user's observation contradicts your model, they are probably right. "MacBook says only once, phone views forever" was reported three times and explained away twice before it was recognised as the bug it was. The user can see the one surface we cannot.
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.
- 8d ago First seen · 152 lines · 2,392 tokens per session scan A 6d4b8947881d
whatsapp-mcp-server CLAUDE.md is an instructions file published in the GitHub repository HalemoGPA/whatsapp-mcp-server (5 stars, last pushed yesterday), licensed MIT. It adds 2,392 tokens to every session, about $0.0120 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.