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 favcrm/mcp --skill favcrm-channel-setupgit clone --depth 1 https://github.com/favcrm/mcpWrote 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/favcrm/mcp/favcrm-channel-setup)<a href="https://agentmods.dev/skills/favcrm/mcp/favcrm-channel-setup"><img src="https://agentmods.dev/badge/skills/favcrm/mcp/favcrm-channel-setup/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/favcrm/mcp/favcrm-channel-setup"><img src="https://agentmods.dev/badge/skills/favcrm/mcp/favcrm-channel-setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00364 |
| Opus 5 | $0.00016 | $0.00182 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
favcrm-channel-setup 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 9d 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
FavCRM Channel Setup
Use this skill when a merchant asks to connect WhatsApp Business or diagnose whether a communication channel is ready.
Operating Rules
- Check current state first with
get_whatsapp_connection_status. - Create a browser handoff only when WhatsApp is not connected or the user explicitly wants to reconnect.
- Use
create_whatsapp_connect_linkfor Meta Embedded Signup. Meta requires a browser interaction; the agent cannot complete this fully headlessly. - After the user finishes the browser flow, call
get_whatsapp_connection_statusagain. - For plan or module blockers, call
check_plan_operationand show any returned upgrade action.
CLI Flow
favcrm whatsapp status
favcrm whatsapp connect --mode cloud-api
favcrm whatsapp status
Use --mode coexistence only when the user is connecting a WhatsApp Business App number that should coexist with Cloud API.
MCP Flow
- Call
get_whatsapp_connection_status. - If not connected, call
create_whatsapp_connect_linkwithonboardingMode. - Ask the user to open the returned
urlin a browser. - When they confirm completion, call
get_whatsapp_connection_status. - Report WABA ID, phone number ID, verified name, and any pending session state.
Failure Handling
- Expired session: create a new connect link.
- Browser flow abandoned: keep the pending session visible and ask the user to retry.
- Plan/module blocked: call
check_plan_operationfor modulewhatsappand surface upgrade instructions.
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.
- 9d ago First seen · 41 lines · 32 tokens per session scan A 9711d9d8d323
favcrm-channel-setup is a skill published in the GitHub repository favcrm/mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 364 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.
Other skills, from other repositories
daily-briefing
Start your day with a prioritized CRM briefing — works for any monday CRM setup: pipeline, contacts, accounts, leads, or no board at all. Use when someone says 'morning briefing', 'daily brief', 'what's on my plate today', 'catch me up on my deals', 'what needs attention', 'what needs my attention', 'anything urgent…
meeting-to-deal
Turn meeting transcripts into deal updates — key points, commitments, and next steps posted to matching CRM deals automatically. Auto-creates contacts for new attendees. Use when someone says "log my meetings to deals", "update CRM from calls", "what did I commit to in meetings", "sync notetaker", "log this meeting"…
multichannel-ecommerce
Manage e-commerce operations across multiple marketplaces and channels. Inventory sync, order routing, listing management, and unified analytics for Amazon, Shopify, Walmart, eBay, Etsy, and TikTok Shop.
Technical Debt Tracking with PMAT
Tracks and manages technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: User asks about technical debt, TODO comments, or code quality issues Planning sprint work and need to prioritize debt repayment Conducting code audits or technical debt assessments Tracking debt accumulation…
repo-harness-product
Canonical rule owner for PRD drafting, Sprint planning/execution, and native Goal-session preparation from repo-harness planning artifacts.
repo-new
A guarded workflow for creating a new IWE repository, including its name, data classification, ownership, readers, registry entry, and starter structure.