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 north-star-metricsgit 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/north-star-metrics)<a href="https://agentmods.dev/skills/impactbrussels/founderos/north-star-metrics"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/north-star-metrics/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/north-star-metrics"><img src="https://agentmods.dev/badge/skills/impactbrussels/founderos/north-star-metrics.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 | $0.00113 | $0.01309 |
| Opus 5 | $0.00056 | $0.00655 |
| Sonnet 5 | $0.00023 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
north-star-metrics 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
North-Star Metrics
First-time founders either track nothing or track everything - both leave them steering blind.
A dashboard with forty numbers is a dashboard with zero decisions. This skill cuts through it:
one north-star metric that genuinely captures the value [STARTUP_NAME] delivers to [ICP],
the handful of input metrics that actually move it, and the one focus metric that matters
right now at your stage. Everything else is noise until it isn't.
The method
Built on the Founder OS scaffold (High tier). Full frameworks, tables and examples in references/metrics.md.
Step 1 - Find the metric that captures delivered value
Your north star is the single number that best reflects the value customers actually get - so when it goes up, the customer is better off and so is the business. Ask:
- What does
[ICP]do when[STARTUP_NAME]is genuinely working for them? - Which number rises because they got value, not because of a one-off push? A good north star ties the customer's win to your business's win. Use the by-type examples in the reference as illustrations - pick the spirit, not the template.
Step 2 - Separate it from vanity metrics
A vanity metric goes up and to the right and tells you nothing you can act on. Test each candidate:
- Does it reflect value delivered, or just activity? (signups ≠ value; active usage might be)
- Can it go down, and would that mean something real? (a metric that only rises is suspect)
- Does it drive a decision? If a number wouldn't change what you do, stop tracking it. The vanity-vs-real table in the reference makes the cut.
Step 3 - Map the 2-4 input metrics that move it
A north star is a lagging outcome - you can't optimise it directly. Build a short input-metric tree: the 2-4 levers that, when they move, move the north star. Each input should be something a team can actually influence this quarter (e.g. acquisition, activation, retention, frequency, or referral - whichever genuinely drives your north star). Keep it to a handful; the tree is for focus, not completeness.
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.
- 10d ago First seen · 94 lines · 113 tokens per session scan A 9b7ded88efb3
north-star-metrics is a skill published in the GitHub repository impactbrussels/FounderOS (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,309 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.