Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Relay Whatsapp Dms Agent

ASecurity

WhatsApp message relay for OpenClaw v0.2.0. Routes third-party DMs to a relay agent that forwards them to the main agent via sessions_send. The main agent notifies the owner with a suggested response. Supports direct number allowlists.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgosecurity

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill relay-whatsapp-dms-agent --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Relay Whatsapp Dms Agent?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Relay Whatsapp Dms Agent
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-relay-whatsapp-dms-agent/badge)](https://www.skillsdirectory.com/skills/rondoflow-relay-whatsapp-dms-agent)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: relay-whatsapp-dms-agent
description: "WhatsApp message relay for OpenClaw v0.2.0. Routes third-party DMs to a relay agent that forwards them to the main agent via sessions_send. The main agent notifies the owner with a suggested response. Supports direct number allowlists."
category: "AI & Agents"
author: community
version: "0.2.1"
icon: bot
---

# wa-relay v0.2.0

Routes third-party WhatsApp DMs through a relay agent that forwards messages to the main agent via `sessions_send`. The main agent notifies the owner and proposes a response.

## How It Works

1. **Third-party** sends a WhatsApp message
2. **Relay agent** receives it, forwards via `sessions_send` to the main agent session, and responds `NO_REPLY` (nothing sent back to the sender)
3. **Main agent** receives the inter-session message, notifies the **owner** on WhatsApp with the message and a suggested response
4. **Owner** decides: use the suggestion, modify it, or write something else
5. **Main agent** sends the response to the third party

### Direct number allowlist

Numbers in the allowlist bypass the relay entirely and go straight to the main agent (same as the owner).

## Setup

1. Run `scripts/setup.sh <owner-phone-number>` — creates relay workspace, patches main agent SOUL.md
2. Run `scripts/configure.sh <owner-phone-number> [direct-numbers]` — generates routing config
3. Apply the generated config (see `references/SETUP.md`)

## Requirements

- OpenClaw v2026.2.14+ with WhatsApp channel configured
- Owner's phone number in international format (e.g. `+573001234567`)

## Security Notes

This skill performs two actions that require elevated access. Both are necessary for multi-agent WhatsApp routing to work and are explained here for transparency:

### 1. Auth credential sharing
The setup script copies `auth-profiles.json` from the main agent to the relay agent. This is required because OpenClaw agents have isolated auth — without shared credentials, the relay agent cannot authenticate with any model provider and will silently fail. The script asks for confirmation before copying.

### 2. Session ID regex patch (temporary)
OpenClaw's session ID validator rejects `:` and `+` characters that WhatsApp phone-number routing generates (e.g. `agent:wa-relay:whatsapp:+15551234567`). The setup script patches the `SAFE_SESSION_ID_RE` regex in OpenClaw's dist files to allow these characters. This is a known bug (openclaw/openclaw#16211) with an open fix (PR #16531). Once merged, this patch becomes unnecessary and can be reverted. The script creates `.bak` backups and asks for confirmation before patching.

### 3. Main agent SOUL.md modification
The setup script appends a "Relay de WhatsApp" section to the main agent's SOUL.md so it knows how to handle forwarded messages. Review the added section after setup.

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →