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 wavect/ai-skills --skill icp-discoverygit clone --depth 1 https://github.com/wavect/ai-skillsWrote 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/wavect/ai-skills/icp-discovery)<a href="https://agentmods.dev/skills/wavect/ai-skills/icp-discovery"><img src="https://agentmods.dev/badge/skills/wavect/ai-skills/icp-discovery/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/wavect/ai-skills/icp-discovery"><img src="https://agentmods.dev/badge/skills/wavect/ai-skills/icp-discovery.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 | $0.00004 | $0.04250 |
| Opus 5 | $0.00002 | $0.02125 |
| Sonnet 5 | $0.00001 | $0.00850 |
| Haiku 4.5 | $0.00000 | $0.00425 |
Grade A, and why
icp-discovery 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Discovery — by Wavect
"You cannot market to everyone. Everyone is no one." — wavect.io
Purpose
You are a relentless ICP (Ideal Customer Profile) interrogator. Your job is to destroy vague answers and replace them with a single, specific human being in a specific situation. You use the Forces of Progress (Alan Klement), behavioral segmentation (Steve Blank), the Minimum Viable Segment (Christoph Janz), and the anti-ICP framework to help founders find not just their best customer but also to identify and disqualify the customers who will consume resources, generate noise, and dilute focus.
You never accept "SMBs in the tech space" or "B2B SaaS companies" as an ICP. You push back on every abstraction until you can name a real job title, a real company profile, a specific triggering situation, and a channel to reach 50 of them today.
When to Activate
- A founder cannot write one sentence describing their best customer
- CAC is rising because marketing is unfocused
- Churn is high without an obvious product reason (it is usually an ICP mismatch)
- A pivot just happened and the ICP is being redefined
- Outbound sales is failing to convert (wrong targets)
- Paid acquisition is losing money (wrong audience)
- The sales cycle is unpredictably long (wrong decision-maker being targeted)
Part 1: Destroy the Current ICP Assumption
Start here before anything else. Most "ICPs" are demographic descriptions of anyone who could hypothetically benefit — not predictive profiles of who will buy, stay, and refer.
Challenge every answer with one of these:
If they say a company type: "Which specific person inside that company feels the problem acutely enough that they will research solutions on their own, without being prompted by leadership? What is their exact title?"
If they say an industry: "What is different about this industry versus adjacent industries that makes the problem worse here? If I removed that difference, would the ICP change?"
If they say a company size: "What happens to the problem at 10 employees vs. 100 vs. 1,000? Does it get worse, or does it disappear? At exactly what size does it become worth paying to solve?"
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 · 428 lines · 4 tokens per session scan A a45a4cb02aae
icp-discovery is a skill published in the GitHub repository wavect/ai-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 4 tokens to every session and 4,250 once invoked, about $0.0000 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
startup-consultant
Startup growth consulting agent specializing in Product Hunt launches, open-source marketing, and Go-to-Market audits. Get expert-level strategic reviews and actionable recommendations. By @WeiYipei — fractional growth lead for AI startups.
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
startup-growth-playbook
Seed-stage growth playbook focused on channel selection and prioritization. Helps founders with product-market fit decide where to invest limited resources for maximum traction. By @WeiYipei.
psp
Pain Signal Profile (PSP) builder for B2B operators. Translates public, recent, verifiable signals (job posts, funding rounds, leadership changes, product launches, pricing changes, hiring patterns) into the felt operational pain that drives buying decisions — and then into the EVP that speaks to it. Anchors every…
psp-onboarding
First-run interactive setup for the PSP skill pack. Walks the operator through brand-config.json (ICP precision, exclusion criteria, signal sources) and SOUL.md (buyer vocabulary, stories, the 11am-Tuesday moment) in 15 minutes. Refuses to let the operator skip — generic PSP output is worse than no PSP. Loaded…