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.
npx agentmods add commands/datacore-one/datacore/whatsappgit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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.
[](https://agentmods.dev/commands/datacore-one/datacore/whatsapp)<a href="https://agentmods.dev/commands/datacore-one/datacore/whatsapp"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/whatsapp.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00006 | $0.00785 |
| Opus 5 | $0.00003 | $0.00392 |
| Sonnet 5 | $0.00001 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WhatsApp integration menu for Datacore.
Usage
/whatsapp [subcommand]
Subcommands
Import
Process .txt chat exports from WhatsApp.
/whatsapp import [--preview] [--space SPACE]
Options:
--preview- Show what would be imported without creating files--space- Target space (default: 0-personal)
Workflow:
- Export chats from WhatsApp mobile app
- Place
.txtfiles in.datacore/state/whatsapp/exports/ - Run
/whatsapp import - Review created contacts in
contacts/people/
Sync
Sync contacts from WAHA gateway (requires active session).
/whatsapp sync
Gateway
Manage WhatsApp message gateway.
/whatsapp gateway [start|stop|status]
Commands:
start- Start message listenerstop- Stop message listenerstatus- Show gateway status
Send
Send message to a contact.
/whatsapp send "<contact_name>" "<message>"
Example:
/whatsapp send "Ahmed Bin Sulayem" "Following up on our Davos conversation..."
Stats
Show WhatsApp export statistics.
/whatsapp stats
Menu Mode
When run without subcommand, shows interactive menu:
- Import exports - Process .txt chat exports
- Sync contacts - Sync from WAHA gateway
- Start gateway - Start message listener
- Stop gateway - Stop message listener
- Send message - Send to contact
- Status - Show gateway and session status
Examples
# Preview what would be imported
/whatsapp import --preview
# Import to specific space
/whatsapp import --space 1-teamspace
# Check gateway status
/whatsapp gateway status
# Send follow-up message
/whatsapp send "Brett Krause" "Great meeting at Davos! Would love to connect about the gaming fund..."
Instructions
When user runs /whatsapp:
- Without subcommand: Show numbered menu and ask what they'd like to do
- With subcommand: Execute that action directly
For import operations:
- Check if exports exist in
.datacore/state/whatsapp/exports/ - Parse exports using
WhatsAppExportParser - Create contacts using
WhatsAppContactCreator - Report created/matched/skipped counts
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.
- 2d ago First seen · 141 lines · 6 tokens per session scan A 4cdfcb327d42
whatsapp is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 6 tokens to every session and 785 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
open
Open the memex vault in Finder or Obsidian.
telegram-secretary
Claude Code Routines（Anthropic のクラウド実行＝cloud routine）上に常駐する Telegram 秘書の 登録・設定・管理表操作の入口。仕様の SSoT は skills/telegram-secretary/SKILL.md、cloud routine 起動手順は ROUTINEPROMPT.md。.
deja
Search this machine's past AI coding sessions (deja-vu).
prd-triage
Triage pending findings on the active PRD.
prd-archive
Archive the active PRD (blocked until every accepted finding has a receipt).
prd-split
Split the approved PRD into one issue spec per manifest entry.