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 buildfastwithai/gen-ai-experiments --skill customer-findergit clone --depth 1 https://github.com/buildfastwithai/gen-ai-experimentsWrote 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/buildfastwithai/gen-ai-experiments/customer-finder)<a href="https://agentmods.dev/skills/buildfastwithai/gen-ai-experiments/customer-finder"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/customer-finder/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/buildfastwithai/gen-ai-experiments/customer-finder"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/customer-finder.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 | $0.00093 | $0.01113 |
| Opus 5 | $0.00046 | $0.00557 |
| Sonnet 5 | $0.00019 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
customer-finder 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 10d 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.
This is a copy
97% identical to first-customer-finder — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Finder
Turn a startup URL or product description into a short, evidence-backed list of plausible first customers. Use public signals, preserve privacy, and distinguish a prospect from a confirmed buyer.
Read references/research-framework.md before researching or scoring prospects. Read references/report-artifact.md before creating the final report.
Workflow
1. Understand the product
- Inspect the supplied URL, repository, landing-page copy, or product description.
- Identify the product, outcome, buyer, user, price or buying motion, geography, and strongest use case.
- Define one primary ICP, one adjacent ICP, pain triggers, positive signals, and disqualifiers.
- Infer missing context when safe and label the inference. Ask one concise question only when ambiguity would materially change the search.
2. Build a public-signal search plan
Search current public sources for:
- explicit tool or alternative requests
- first-person descriptions of the target problem
- manual workflows and repeated workaround complaints
- migration, churn, or competitor-frustration signals
- public company changes that create timing, such as hiring, launching, expanding, or adopting a relevant workflow
Use multiple query angles and source types. Prefer original pages over search snippets. Record the source URL, source type, publication date when visible, and the exact evidence supporting qualification.
3. Research safely
- Use public, intentionally shared professional or business information only.
- Do not bypass login walls, paywalls, access controls, rate limits, or robots restrictions.
- Do not use data brokers, leaked datasets, private groups, personal email discovery, phone enrichment, or sensitive personal information.
- Do not infer protected traits or target people using health, financial hardship, political belief, sexuality, religion, or other sensitive attributes.
- Prefer companies, public professional profiles, public requests, and community posts relevant to the product.
- Quote minimally and paraphrase by default. Link every material pain or timing signal.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 102 lines · 93 tokens per session scan A 03492190daa4
customer-finder is a skill published in the GitHub repository buildfastwithai/gen-ai-experiments (763 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,113 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to first-customer-finder, differing in 4 lines, and is treated as a copy.
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…