wa

wa is a skill for Claude Code, Codex from floomhq/moto. It costs 59 tokens per session (1,005 once invoked), scanned A, original, MIT.

A skill for reading and sending WhatsApp messages through the local WhatsApp database and a verified sending script. It includes rules requiring confirmation before any message is sent.

In plain words
What is it for?
Finding contacts, reading recent direct messages, resolving the recipient’s verified phone number, and sending a message after explicit confirmation.
Why use it?
It reduces the risk of reading the wrong conversation or sending confidential information to the wrong number.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/floomhq/moto/wa
Any agent
npx skills add floomhq/moto --skill wa
Clone the repo
git clone --depth 1 https://github.com/floomhq/moto

Made for: Claude Code, 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 wa

README.md
[![agentmods](https://agentmods.dev/badge/skills/floomhq/moto/wa.svg)](https://agentmods.dev/skills/floomhq/moto/wa)
Your own site
<a href="https://agentmods.dev/skills/floomhq/moto/wa"><img src="https://agentmods.dev/badge/skills/floomhq/moto/wa.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,005 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.01005
Opus 5 $0.00030 $0.00502
Sonnet 5 $0.00012 $0.00201
Haiku 4.5 $0.00006 $0.00101

Measured 5d ago against content hash f9bb1cdd8f5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

wa 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 5d 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.

claude/skills/wa/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WhatsApp Skill

CRITICAL: Sending Rules

NEVER send without explicit confirmation. Wrong-number sends leak confidential info.

  • Block unverified sends via a PreToolUse hook (see hooks/).
  • NEVER construct phone numbers from memory.
  • Discussion/brainstorming is NOT a send instruction. Only "send", "go", "send it" counts.

Only send flow:

  1. Run your verified send script (dry run: resolves JID, shows phone, exits without sending)
  2. Show the user the resolved phone number
  3. Wait for explicit "yes" / "send" / "go"
  4. Run with --confirmed flag

Reading Messages

Step 1: Copy the DB

DB_SOURCE="<PATH_TO_WHATSAPP_CHATSTORE_SQLITE>"
cp "$DB_SOURCE" /tmp/wa-chat.sqlite

If the copy fails, the source is unavailable. Do not proceed; tell the user.

Step 2: Find a contact

sqlite3 /tmp/wa-chat.sqlite "
SELECT ZCONTACTJID, ZCONTACTIDENTIFIER, ZPARTNERNAME
FROM ZWACHATSESSION
WHERE ZPARTNERNAME LIKE '%Name%';
"

Step 3: Read DM messages

sqlite3 /tmp/wa-chat.sqlite "
SELECT ZFROMJID, ZTEXT, datetime(ZMESSAGEDATE + 978307200, 'unixepoch') as msg_time
FROM ZWAMESSAGE
WHERE ZFROMJID LIKE '%PHONE_OR_LID%'
ORDER BY ZMESSAGEDATE DESC
LIMIT 20;
"

Replace PHONE_OR_LID with phone digits or LID from step 2 (no +, no spaces).

Step 4: Read group messages

sqlite3 /tmp/wa-chat.sqlite "
SELECT ZMEMBERJID, ZTEXT, datetime(ZMESSAGEDATE + 978307200, 'unixepoch') as msg_time
FROM ZWAMESSAGE
WHERE ZCHATSESSION IN (
  SELECT Z_PK FROM ZWACHATSESSION WHERE ZPARTNERNAME LIKE '%GroupName%'
)
ORDER BY ZMESSAGEDATE DESC
LIMIT 20;
"

Step 5: Read full conversation (both sides)

sqlite3 /tmp/wa-chat.sqlite "
SELECT
  CASE WHEN ZFROMJID IS NULL THEN 'Me' ELSE ZFROMJID END as sender,
  ZTEXT,
  datetime(ZMESSAGEDATE + 978307200, 'unixepoch') as msg_time
FROM ZWAMESSAGE
WHERE ZCHATSESSION IN (
  SELECT Z_PK FROM ZWACHATSESSION WHERE ZCONTACTJID LIKE '%PHONE_OR_LID%'
)
  AND ZTEXT IS NOT NULL
ORDER BY ZMESSAGEDATE DESC
LIMIT 30;
"

Read the full file on GitHub · 136 lines

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. 5d ago First seen · 136 lines · 59 tokens per session scan A f9bb1cdd8f5a

Subscribe to this mod's changes

wa is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,005 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

tdd-rust

TDD workflow for RTK filter development. Red-Green-Refactor with Rust idioms. Real fixtures, token savings assertions, snapshot tests with insta. Auto-triggers on new filter implementation.

rtk-ai/rtk · 45 tokens

rtk-optimizer

Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.

FlorianBruniaux/claude-code-ultimate-guide · 44 tokens

session-save

Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.

FlorianBruniaux/claude-code-ultimate-guide · 31 tokens

handoff-create

Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.

FlorianBruniaux/claude-code-ultimate-guide · 53 tokens

handoff-update

Update an existing handoff document with current session progress. Applies section-specific merge rules: append-only for Work Done (never deletes history), replace for Status and Next Steps, merge for Files and Discoveries. Falls back to creating a new handoff if no source file is found.

FlorianBruniaux/claude-code-ultimate-guide · 60 tokens

handoff-resume

Load a handoff document and resume work from where a previous session left off. Parses scope, file references, completed work, and next steps, then confirms understanding before proceeding.

FlorianBruniaux/claude-code-ultimate-guide · 40 tokens