Borrowing it
Nothing to install: this file belongs to bobberrisford/affiliatemcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bobberrisford/affiliatemcp/main/.claude/skills/onboarding-loop/SKILL.mdgit clone --depth 1 https://github.com/bobberrisford/affiliatemcpWrote 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/bobberrisford/affiliatemcp/onboarding-loop)<a href="https://agentmods.dev/skills/bobberrisford/affiliatemcp/onboarding-loop"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/onboarding-loop/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/bobberrisford/affiliatemcp/onboarding-loop"><img src="https://agentmods.dev/badge/skills/bobberrisford/affiliatemcp/onboarding-loop.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 | $0.00127 | $0.00943 |
| Opus 5 | $0.00063 | $0.00472 |
| Sonnet 5 | $0.00025 | $0.00189 |
| Haiku 4.5 | $0.00013 | $0.00094 |
Grade A, and why
onboarding-loop 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 11d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating instructions
You prepare the lifecycle email a hosted user should receive, as Gmail drafts
only. You never send. This honours the authority boundary in
docs/decisions/2026-07-20-agentic-company-operations.md and the operating
model in docs/product/solo-50k-revenue-plan.md section 6 ("onboarding replaces
account management").
This is not the agency client-onboarding skill (which records a client's
strategy and KPI targets). This loop is about bringing a new product sign-up
to first value and keeping accounts active.
The targeting dependency (read this first)
You need a signal of who to contact: who just signed up, who connected but
has not run a report, who has gone quiet. That roster lives on the hosted side.
Per hosted/src/digest.ts, the active-subscriber roster is enumerated
in-process from HOSTED_BILLING KV and never exposed over HTTP, so an agent
session cannot read it directly.
Therefore this loop is partial by design until a safe read-only path is connected:
- If the operator supplies a target list (or a connected read path exists), prepare drafts for those users.
- If no target signal is available, say so plainly in the brief ("onboarding: no sign-up signal connected") and prepare reusable draft templates (below) rather than guessing at recipients. Never invent sign-ups or email addresses.
Do not build a new data egress from the hosted service to get this signal; that
would need its own decision under the custody record. Reuse the existing
listActiveSubscribers enumeration on the hosted side if and when onboarding
signals are surfaced through an approved read path.
The three lifecycle drafts
Prepare whichever apply to a given user (or as templates when untargeted):
- First value (new sign-up). Welcome, the single next action to see their
own numbers, and what to expect. The first-value report itself reuses the
digest compose path (
composeDigestForUserinsrc/hosted-digest/run.ts, the same engine behind the weekly digest) rather than any new report code. Keep it to one clear call to action. - Activation nudge (connected, no report yet). A short prompt with the exact first thing to ask in their MCP client, framed around their own data.
- Re-engagement (dormant). A light, non-pushy check-in that leads with a concrete recent value the product can show, not a plea to come back. Honour unsubscribe and frequency norms; one re-engagement draft, not a sequence that would read as pressure.
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.
- 11d ago First seen · 78 lines · 127 tokens per session scan A 5bf48e4e6a22
onboarding-loop is a skill published in the GitHub repository bobberrisford/affiliatemcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 943 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…