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 S3YED/appie-kit --skill ibrahim-lead-followupgit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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/s3yed/appie-kit/ibrahim-lead-followup)<a href="https://agentmods.dev/skills/s3yed/appie-kit/ibrahim-lead-followup"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ibrahim-lead-followup/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/s3yed/appie-kit/ibrahim-lead-followup"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/ibrahim-lead-followup.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 | $0.00048 | $0.01054 |
| Opus 5 | $0.00024 | $0.00527 |
| Sonnet 5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
ibrahim-lead-followup 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ibrahim Lead WhatsApp Follow-up
When to Use
Use this skill when Ibrahim asks you to send follow-ups, drafts, or outreach messages to leads in his coaching pipeline. Automatically personalized per funnel stage.
Brand Voice Rules (non-negotiable)
Reference: kratos-operations → references/voice-profile.md for full voice analysis from 211 messages.
- No em dashes — ever. Use periods or commas instead.
- No metaphors or flowery language. Short, direct sentences.
- Sound human, not AI slop. No corporate filler. No apostrophes (
youre,heres,thats,im,dont,bc). - Quiet masculinity with direct accountability. Never shout. Never shame. Make them feel seen before they feel corrected. Validate first, redirect second.
- Must hit emotional pain/drive — not surface level. Reference their specific situation.
- Message architecture follows 4 types: Welcome (Type A, ~25 words), Quick Win (Type B, 50-80 words), Honest Read (Type C, 150-400 words), Logistics (Type D, 1-8 words). See voice-profile.md for templates.
- Aspiration over shame — never "I've let myself go." Always "unlocked potential."
- Use brother/sister for gender respect. Never "guys" — use "everyone."
- Signature phrases to use: "You told me something that stuck with me", "So here's my honest read on your next step", "This is the surface level. The full system...", "does that make sense?", "If nothing changed and a year from now..."
- Never: Use corporate language. Beg or chase. Compare negatively. Give up on quiet leads — keep showing up with "Salam, any updates?"
Funnel Stage Templates
Stage 1: Just Entered Giveaway (Welcome)
Goal: Make them feel seen, explain next step, get them to save contact. Template: "Brother/Sister [Name], saw your entry. I read through your answers. [Reference one specific thing they wrote]. The challenge starts [date]. First thing: [one small win they can get today]. Make sure you save my number so we stay connected."
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.
- 8d ago First seen · 70 lines · 48 tokens per session scan A a682e76886de
ibrahim-lead-followup is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 16d ago), licensed MIT. It adds 48 tokens to every session and 1,054 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 2026-09-03.
Other skills, from other repositories
c-messaging
Send and read messages via imsg (iMessage) and wacli (WhatsApp). Supports sending to individuals or groups, reading recent conversations, and checking unread messages across both platforms.
c-telegram
Bidirectional Telegram bridge — talk to Claude from your phone. Built into OpenPaw.
c-slack
Send messages and upload files to Slack channels using the slack CLI. Supports direct messages, channel posts, file uploads, and thread replies.
whatsapp-automation
WhatsApp Business automation - customer support, notifications, chatbots, and broadcast messaging.
messaging
Send messages to users via WhatsApp and other connected channels. Use when asked to notify someone, send a message, reply to a contact, message a group, or proactively communicate through WhatsApp. Supports text, images, documents, audio, video, and stickers. Also provides group etiquette for observing group…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.