A setup tool for connecting a coding agent to WhatsApp, the messaging service. It checks login status, access rules, and linked-device authentication.

Use it to check the WhatsApp connection, import an existing login, review allowed senders, and get guidance for pairing users or locking access down.

It removes the need to inspect authentication files and access settings by hand. It also explains what to do when WhatsApp is not connected or no users are allowed.

configure — Skill for Claude Code by PenguinMiaou

Install

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.

Any agent

npx skills add PenguinMiaou/claude-channel-whatsapp --skill configure

Clone the repo

git clone --depth 1 https://github.com/PenguinMiaou/claude-channel-whatsapp

Made for: Claude Code.

Or install whatsapp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/penguinmiaou/claude-channel-whatsapp/configure/github.svg)](https://agentmods.dev/skills/penguinmiaou/claude-channel-whatsapp/configure)

Your own site

<a href="https://agentmods.dev/skills/penguinmiaou/claude-channel-whatsapp/configure"><img src="https://agentmods.dev/badge/skills/penguinmiaou/claude-channel-whatsapp/configure/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/penguinmiaou/claude-channel-whatsapp/configure"><img src="https://agentmods.dev/badge/skills/penguinmiaou/claude-channel-whatsapp/configure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 507 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00034	$0.00507
Opus 5	$0.00017	$0.00253
Sonnet 5	$0.00007	$0.00101
Haiku 4.5	$0.00003	$0.00051

Measured 12d ago against content hash 23d94eea2a04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

configure 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 12d 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.

skills/configure/SKILL.md · 67 lines

What it actually says

/whatsapp:configure — WhatsApp Channel Setup

Unlike Telegram which uses a bot token, WhatsApp uses device-linked auth via @whiskeysockets/baileys. Auth state lives in ~/.claude/channels/whatsapp/auth/.

Arguments passed: $ARGUMENTS

Dispatch on arguments

No args — status and guidance

Auth — check if ~/.claude/channels/whatsapp/auth/creds.json exists. If yes, show "authenticated" with brief info. If no, show "not authenticated".
Access — read ~/.claude/channels/whatsapp/access.json (missing = defaults). Show:
- DM policy and what it means
- Allowed senders: count and phone numbers
- Pending pairings
What next — concrete guidance:
- No auth → explain they need to set up auth (import from another Baileys setup or link a new device)
- Auth exists, nobody allowed → tell them to message from WhatsApp, then pair with /whatsapp:access pair <code>
- Auth + people allowed → "Ready."

Push toward lockdown (allowlist mode) once users are paired.

`import`

Import auth from another Baileys-based WhatsApp setup:

Ask the user for the source directory path containing creds.json
Copy all files to ~/.claude/channels/whatsapp/auth/
Confirm

`clear`

Remove auth state to force re-authentication:

Remove all files in ~/.claude/channels/whatsapp/auth/
Confirm — note that re-auth will require linking the device again

Implementation notes

Auth is managed by baileys' useMultiFileAuthState — don't manually edit creds.json.
Connection issues: check ~/.claude/channels/whatsapp/auth/creds.json exists and has valid content.

Changes

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.

12d ago First seen · 67 lines · 34 tokens per session scan A 23d94eea2a04

Subscribe to this mod's changes

configure is a skill published in the GitHub repository PenguinMiaou/claude-channel-whatsapp (2 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 507 once invoked, about $0.0002 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.

Claude Code anthropic mcp plugin whatsapp

client-deliverables

Create and refine consulting reports, decision memos, and executive presentations, including storylines, exhibits, visual design, and artifact review. Use for board readouts, investment committee memos, steering updates, and final reports. For sales proposals and pitch decks, use proposal-development when available.

anotb/management-consulting-plugin · 63 tokens

strategic-analysis

Structure an ambiguous business decision, test competing explanations, and recommend a course using evidence. Use for growth, market entry, competitive positioning, business models, and portfolio choices. For execution of an approved direction, use implementation-planning when available.

anotb/management-consulting-plugin · 52 tokens

thought-leadership

Develop evidence-backed points of view, white papers, case studies, industry briefs, and research reports for a consulting audience. Use to turn research or permitted engagement experience into a useful, defensible argument.

anotb/management-consulting-plugin · 45 tokens

change-management

Diagnose adoption barriers and design organizational change, stakeholder engagement, communications, training, and reinforcement. Use for system rollouts, new operating models, integration, culture change, and adoption measurement.

anotb/management-consulting-plugin · 41 tokens

due-diligence

Investigate commercial, operational, financial, strategic, and technology claims for acquisition, investment, partnership, or vendor decisions. Use for data-room analysis, quality of earnings, customer concentration, working capital, synergies, and diligence recommendations.