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 skills add TheSmokeDev/taskchad-os --skill whatsapp-bridgegit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/skills/thesmokedev/taskchad-os/whatsapp-bridge)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/whatsapp-bridge"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/whatsapp-bridge/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.
<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/whatsapp-bridge"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/whatsapp-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.00486 |
| Opus 5.5 | $0.00025 | $0.00194 |
| Sonnet 5.5 | $0.00013 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
whatsapp-bridge 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 2mo 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.
What it actually says
WhatsApp Bridge
Wire WhatsApp into the existing chat interface as one more channel adapter. The
framework already abstracts Telegram/Slack/Discord (see .claude/sections/02_*);
this adds a WhatsApp adapter behind the same interface — it does not fork the
engine.
Provider
Use the WhatsApp Cloud API (Meta) or an equivalent gateway (e.g. Twilio for WhatsApp). Both deliver inbound messages via webhook and accept outbound sends via REST.
Required .env values:
WHATSAPP_PHONE_NUMBER_ID=
WHATSAPP_ACCESS_TOKEN=
WHATSAPP_VERIFY_TOKEN= # for webhook handshake
WHATSAPP_ALLOWED_NUMBERS= # comma-separated allowlist
Adapter contract
Implement the channel adapter to match the existing chat interface:
- Inbound — verify the webhook signature, drop senders not in
WHATSAPP_ALLOWED_NUMBERS, normalize the payload to the engine's message shape, and hand it to the router. - Outbound — render the engine's reply to WhatsApp's message format and POST it to the Cloud API.
Security
- Enforce
WHATSAPP_ALLOWED_NUMBERSon every inbound message — mirror theTELEGRAM_ALLOWED_USER_IDSallowlist pattern. Unknown senders are dropped, not answered. - Outbound sends are mutations: route them through the
chat.sendcapability gate with an audit trail. Never call the WhatsApp API directly from a tool. - Verify the webhook
X-Hub-Signature-256HMAC before trusting any payload.
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.
- 2mo ago First seen · 57 lines · 63 tokens per session scan A 5cd53c131fdb
whatsapp-bridge is a skill published in the GitHub repository TheSmokeDev/taskchad-os (28 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 486 once invoked, about $0.0003 per session on Opus 5.5. 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.
whatsapp-bridge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| whatsapp-bridgeTheSmokeDev/taskchad-os | Skill | 28 | 1mo ago | MIT | A | 63 | Claude Code, Codex |
| secret-warnmycelium-hq/ai-brain-starter | Skill | 50 | yesterday | MIT | B | 121 | Claude Code |
| agent-crdt-synchronizerruvnet/ruflo | Skill | 82k | today | MIT | A | 25 | Claude Code |
| agent-quorum-managerruvnet/ruflo | Skill | 82k | today | MIT | A | 18 | Claude Code |
| flow-nexus-swarmruvnet/ruflo | Skill | 82k | today | MIT | A | 20 | Claude Code |
| agent-dev-backend-apiruvnet/ruflo | Skill | 82k | today | MIT | A | 22 | Claude Code |
| agent-docs-api-openapiruvnet/ruflo | Skill | 82k | today | MIT | A | 24 | Claude Code |