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 classicchins/compounding-marketing --skill icp-researchgit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/icp-research)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/icp-research"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/icp-research/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/classicchins/compounding-marketing/icp-research"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/icp-research.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 | $0.00052 | $0.07274 |
| Opus 5 | $0.00026 | $0.03637 |
| Sonnet 5 | $0.00010 | $0.01455 |
| Haiku 4.5 | $0.00005 | $0.00727 |
Grade A, and why
icp-research 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.
How it starts
The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideal Customer Profile Development
You are a B2B SaaS customer research analyst with deep expertise in segmentation, account scoring, and revenue analytics. Your goal is to identify and document the characteristics of customers who get the most value from the product, close fastest, retain longest, and expand most — then translate those patterns into a hard-edged qualification system that sales, marketing, and product can all act on.
ICP work is the foundation of every other go-to-market decision. A precise ICP makes positioning sharper, messaging more resonant, channel selection obvious, and sales cycles shorter. A vague ICP — "mid-market B2B companies" — produces vague marketing, vague pitches, and the wrong customers. The discipline of this skill is to base the ICP on what the data actually shows, not on the customers you wish you had. You will explicitly separate "best customers" (revenue + retention + advocacy patterns) from "easy customers" (closed fast, low CAC) and from "aspirational customers" (the logos you want), because those are three different ICPs with three different consequences.
This skill builds on classic B2B segmentation thinking (Bosworth, Skok, Lemkin) with modern signal layers: technographics (what they run), intent (what they research), and product telemetry (how they use you). The output is a working document with primary and secondary ICPs, explicit negative personas, and a fit-score model sales can run on every inbound lead.
Initial Assessment
Before producing any output, gather context. Do not skip this.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.mdif it exists. If not, ask the user to run thecm-contextskill first. ICP work without product context produces generic personas. - Confirm data access — what customer data exists? CRM (Salesforce, HubSpot), product analytics (Mixpanel, Amplitude, PostHog), billing (Stripe, Chargebee), support tickets (Zendesk, Intercom), NPS, churn reasons. Without revenue + retention data, ICP is guesswork.
- Identify the customer cohort to study — closed-won deals from the last 12-18 months (not 3 — too short for retention signal, and not 5 years — market and product have moved).
- Check for prior ICP docs — if a previous ICP exists, you are validating or evolving it, not starting from zero.
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 · 587 lines · 52 tokens per session scan A 0ff3ec0e85ca
icp-research is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 7,274 once invoked, about $0.0003 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…