wacrawl

wacrawl is a skill for Claude Code, Codex from moltis-org/moltis. It costs 50 tokens per session (801 once invoked), scanned A, original, MIT.

A read-only macOS tool for searching and exporting messages stored by WhatsApp Desktop. It reads WhatsApp's local databases and can create encrypted backups.

In plain words
What is it for?
Use it to check local chat history, list conversations, export messages, synchronize an archive, and create encrypted backups.
Why use it?
It lets you investigate old chats without changing the WhatsApp data. It also provides a local archive when finding information in the desktop app is difficult.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to check local chat history, list conversations, export messages, synchronize…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moltis-org/moltis/wacrawl
About the project

Moltis is a persistent personal agent server written in Rust that runs on hardware controlled by its user. It provides an AI agent with sandboxed command execution, model-provider connections, memory, voice, scheduling, messaging integrations, browser automation, and MCP tools. Its catalogue add-ons extend the agent’s workflows and available tools.

moltis-org/moltis · 2,847 stars · on GitHub · moltis.org

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 moltis-org/moltis --skill wacrawl
Clone the repo
git clone --depth 1 https://github.com/moltis-org/moltis

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 wacrawl

README.md
[![agentmods](https://agentmods.dev/badge/skills/moltis-org/moltis/wacrawl.svg)](https://agentmods.dev/skills/moltis-org/moltis/wacrawl)
Your own site
<a href="https://agentmods.dev/skills/moltis-org/moltis/wacrawl"><img src="https://agentmods.dev/badge/skills/moltis-org/moltis/wacrawl.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 801 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 $0.00050 $0.00801
Opus 5 $0.00025 $0.00400
Sonnet 5 $0.00010 $0.00160
Haiku 4.5 $0.00005 $0.00080

Measured 7d ago against content hash 3787173894d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

wacrawl 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 7d 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.

crates/skills/src/assets/messaging/wacrawl/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wacrawl — WhatsApp Desktop Archive (Read-Only)

wacrawl is a read-only local archive tool for WhatsApp Desktop on macOS. It snapshots the local SQLite databases (ChatStorage.sqlite, ContactsV2.sqlite) without modifying them. Use it for searching chat history, exporting conversations, and creating encrypted backups.

This is different from wacli — wacrawl is read-only archaeology of local data; wacli is an active WhatsApp Web client for sending/receiving messages.

Secret Safety

  • wacrawl reads local files only — no API tokens needed.
  • The optional age encryption key at ~/.wacrawl/age.key is auto-generated and must not be printed to agent context.
  • Never read, print, or send ~/.wacrawl/age.key to LLM context.

Prerequisites

  • macOS only (reads WhatsApp Desktop's local SQLite databases).
  • WhatsApp Desktop must be installed and have synced messages.
  • Full Disk Access may be required for the terminal app to read WhatsApp's container.

Health Check

wacrawl doctor

Sync Local Data

wacrawl sync

Snapshots the current state of WhatsApp Desktop's databases into wacrawl's local store.

List Chats

wacrawl chats
wacrawl chats --limit 20
wacrawl chats --json

Search Messages

wacrawl search "query"
wacrawl search "invoice" --limit 20
wacrawl messages --chat <jid> --limit 50
wacrawl messages --chat <jid> --json

Encrypted Backup

wacrawl backup
wacrawl backup --output /path/to/backup/

Creates age-encrypted JSONL.gz shards suitable for Git-backed storage.

Saving to Memory

To save search results or chat exports to Moltis memory for future reference:

  1. Run wacrawl with --json output
  2. Summarize the relevant conversations into a daily digest
  3. Save as memory/whatsapp/YYYY-MM-DD.md

Example workflow:

wacrawl search "project meeting" --json --limit 20

Then write a summary to memory:

# WhatsApp — 2026-04-28

## Key Conversations
- Discussion with Alice about project timeline — agreed on June deadline
- Bob shared the updated budget spreadsheet
- Team group: standup notes, blockers discussed

Read the full file on GitHub · 110 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. 7d ago First seen · 110 lines · 50 tokens per session scan A 3787173894d0

Subscribe to this mod's changes

wacrawl is a skill published in the GitHub repository moltis-org/moltis (2,847 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 801 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.