Borrowing it
Nothing to install: this file belongs to xbirimensah/whatsapp-bridge. 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/xbirimensah/whatsapp-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/xbirimensah/whatsapp-bridgeWrote 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/xbirimensah/whatsapp-bridge/agents-md)<a href="https://agentmods.dev/instructions/xbirimensah/whatsapp-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/xbirimensah/whatsapp-bridge/agents-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/xbirimensah/whatsapp-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/xbirimensah/whatsapp-bridge/agents-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 | $0.03738 | $0.03738 |
| Opus 5 | $0.01869 | $0.01869 |
| Sonnet 5 | $0.00748 | $0.00748 |
| Haiku 4.5 | $0.00374 | $0.00374 |
Grade C, and why
whatsapp-bridge AGENTS.md scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> **Single-session lock.** As of 2026-05, the bridge refuses to boot with more than one paired session under `auth/` and refuses to pair a second number while one already exists. To switch numbers: `rm -rf auth/<name>/` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — whatsapp-bridge
You are an AI / coding agent (Claude Code, Codex, Hermes, custom) working with this repository. This file is the contract: what whatsapp-bridge is, what you can do through it, and the rules you operate under.
What this is
whatsapp-bridge is a self-hosted WhatsApp bridge. It pairs one personal WhatsApp account and exposes it through:
- a token-protected REST API on
http://127.0.0.1:8080(default) - an MCP stdio server (
src/mcp.ts) — your primary surface - a single-page web UI at
/ - an optional outbound webhook that fires on inbound messages
Treat it as personal infrastructure for one operator on one number — not a multi-tenant product.
An optional autoreply sidecar (src/autoreply-*.ts, separate process) consumes the inbound webhook, drafts replies in the operator's voice, and can auto-send through the REST API under policy + safety gates. See docs/autoreply.md for its env vars, routes, and safety contract. The sidecar is not in scope for normal MCP tool work — only touch it when explicitly asked.
Single-session lock. As of 2026-05, the bridge refuses to boot with more than one paired session under
auth/and refuses to pair a second number while one already exists. To switch numbers:rm -rf auth/<name>/and re-pair. Multi-session plumbing (DBsessioncolumn, MCPsessionparam) is intact — just runtime-locked.
Companion docs: README.md covers human setup, the REST table, and env vars; docs/autoreply.md is the autoreply sidecar reference. This file is both the agent-facing contract (tools + safety) and the entry point for working on the source — it does not duplicate the others, so read them when the topic is in scope.
Mental model
If you have the whatsapp-bridge MCP tools wired up, this is how to think:
- A session is one paired phone number (typically
main).list_sessionsreturns the singleton list. - A JID identifies a chat or person. Three forms:
<digits>@s.whatsapp.net— phone-keyed user (PN form, has a phone number)<id>@lid— privacy alias (no phone number; same person may also have a PN JID)<id>@g.us— group chat
- The same person can appear under both a PN and a LID JID. The
jid_aliasestable collapses them on read, andmerge_jidslets you record new mappings when you discover them.
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 · 253 lines · 3,738 tokens per session scan C be022a4617b5
whatsapp-bridge AGENTS.md is an instructions file published in the GitHub repository xbirimensah/whatsapp-bridge (2 stars, last pushed 25d ago), licensed MIT. It adds 3,738 tokens to every session, about $0.0187 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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.