chessclaw: Skill for Codex

.codex/skills/add-whatsapp/SKILL.md

add-whatsapp is a skill for Codex from fmbenhassine/chessclaw. It costs 42 tokens per session (2,013 once invoked), scanned A, original, MIT.

A code-change skill that makes WhatsApp the only messaging channel for ChessClaw, a single-channel assistant. It keeps one direct chat, one workspace, and one persistent session.

In plain words
What is it for?
Use it to switch a fork back to WhatsApp, configure the existing WhatsApp runtime, or confirm that message intake, storage, processing, and replies use one WhatsApp conversation.
Why use it?
It removes leftover support for Telegram, group chats, multiple chat folders, or other parallel messaging routes. This keeps the application aligned with a WhatsApp-only design.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md; mentions Codex.

This is fmbenhassine/chessclaw's own configuration. It tells Codex how to work on chessclaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything chessclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fmbenhassine/chessclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fmbenhassine/chessclaw/main/.codex/skills/add-whatsapp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fmbenhassine/chessclaw

Made for: Codex.

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.

agentmods badge for add-whatsapp

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmbenhassine/chessclaw/add-whatsapp/github.svg)](https://agentmods.dev/skills/fmbenhassine/chessclaw/add-whatsapp)
Your own site
<a href="https://agentmods.dev/skills/fmbenhassine/chessclaw/add-whatsapp"><img src="https://agentmods.dev/badge/skills/fmbenhassine/chessclaw/add-whatsapp/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.

agentmods 80×15 button for add-whatsapp

Your own site · 80×15
<a href="https://agentmods.dev/skills/fmbenhassine/chessclaw/add-whatsapp"><img src="https://agentmods.dev/badge/skills/fmbenhassine/chessclaw/add-whatsapp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,013 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.02013
Opus 5 $0.00021 $0.01007
Sonnet 5 $0.00008 $0.00403
Haiku 4.5 $0.00004 $0.00201

Measured 10d ago against content hash 38d943d3ad88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-whatsapp 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 10d 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.

.codex/skills/add-whatsapp/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Replace Current Transport With WhatsApp

This skill updates ChessClaw so that WhatsApp is the only live messaging transport.

It is intended for the current single-channel architecture. Use it when the user wants to:

  • keep the existing WhatsApp runtime and set it up cleanly
  • switch a fork back from Telegram or another transport to WhatsApp
  • make WhatsApp the only assistant channel

Do not preserve any old multi-channel or multi-chat design. The target architecture is:

  • one direct WhatsApp chat as the assistant channel
  • one assistant workspace
  • one persistent session
  • no parallel Telegram or secondary transport runtime

What This Skill Should Do

When executed, this skill should transform or confirm the codebase so that:

  1. WhatsApp is the only live messaging transport
  2. The single-channel runtime stays intact
  3. The assistant still uses:
    • assistant/AGENTS.md
    • assistant/
    • data/session/.codex/
    • data/ipc/
  4. The request lifecycle remains:
    • transport ingest
    • SQLite persistence
    • single message queue
    • Apple container
    • Codex thread
    • transport reply

Do not reintroduce:

  • group registration
  • registered_groups
  • per-chat folders
  • per-chat sessions
  • per-chat queueing
  • chat privilege models

Questions To Ask

Before editing code, ask the user:

  1. Should the assistant use the authenticated WhatsApp self-chat, or one explicit direct 1:1 chat JID?
  2. If not the self-chat, what exact WhatsApp JID should be used?

Prerequisites

1. Install WhatsApp Dependencies

If the repo does not already include the WhatsApp transport dependencies, install them:

npm install @whiskeysockets/baileys qrcode-terminal
npm install -D @types/qrcode-terminal

If the current fork already has these dependencies, do not duplicate or replace them.

2. Authenticate With WhatsApp

Tell the user:

I need you to authenticate ChessClaw with WhatsApp.

  1. Run npm run auth
  2. Open WhatsApp on your phone
  3. Go to Settings -> Linked Devices -> Link a Device
  4. Scan the QR code shown in the terminal

Read the full file on GitHub · 309 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 309 lines · 42 tokens per session scan A 38d943d3ad88

Subscribe to this mod's changes

add-whatsapp is a skill published in the GitHub repository fmbenhassine/chessclaw (5 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 2,013 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.