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 impactbrussels/FounderOS --skill find-first-customersgit clone --depth 1 https://github.com/impactbrussels/FounderOSWrote 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/impactbrussels/founderos/find-first-customers)<a href="https://agentmods.dev/skills/impactbrussels/founderos/find-first-customers"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/find-first-customers/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/impactbrussels/founderos/find-first-customers"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/find-first-customers.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 | $0.00125 | $0.01358 |
| Opus 5 | $0.00063 | $0.00679 |
| Sonnet 5 | $0.00025 | $0.00272 |
| Haiku 4.5 | $0.00013 | $0.00136 |
Grade A, and why
find-first-customers 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Your First Customers
The first ~10 paying customers don't come from a funnel - they come from a founder doing things that don't scale: a hand-built list, personal messages, real conversations, and a direct ask for money. First-timers stall here because selling feels uncomfortable, so they hide behind building features and waiting for inbound that never arrives. This skill gives you a concrete, repeatable motion to go get them by hand - and learn from every "no."
The method
Built on the Founder OS scaffold (High tier). Full templates in references/early-sales.md.
Step 1 - Build a target list from the ICP
You can't sell to "everyone." Translate [ICP] into a list of named, reachable people - 30-50
to start - who plausibly have [PROBLEM] right now. Use the sourcing tactics in references
(communities, search, your network's network, competitor reviews). Each row is a real human, not a
segment. Research enough to know why this person, before you write a word - generic blasts get
generic silence.
Step 2 - Pick ONE outbound channel
Choose the single [CHANNEL] where you can actually reach this list and they'll actually read it:
cold email, LinkedIn/DM, a warm intro, or a community post. One channel, done well and measured,
beats five done half-heartedly. Match the channel to where [ICP] already pays attention.
Step 3 - Write a short, non-spammy message
Good early outreach is short, specific, and about them, not your product. Reference why you're
reaching this person, name the [PROBLEM] in their words, and make a small, low-friction ask
(usually a 15-minute conversation - not "buy now"). Use the good/bad examples in references.
A draft is not a sent message - write three, pick the tightest, then send. Personalize the opening
line; templated flattery reads as spam.
Step 4 - Run the conversation to a clear ask
The call has a job: confirm the problem, see if you're a fit, and make one explicit ask - a trial, a pilot, or a purchase. Use the qualifying questions in references to disqualify fast (your time is the scarce resource). Don't pitch into a vacuum; ask, listen, then ask for the close. If they're a fit, name the next step and a date. Vague "let's stay in touch" is a polite no.
What ships with it
1 file 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.
- 9d ago First seen · 89 lines · 125 tokens per session scan A 6de6285a0e7c
find-first-customers is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 1,358 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
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.