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 san-npm/skills-ws --skill growth-hackinggit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/growth-hacking)<a href="https://agentmods.dev/skills/san-npm/skills-ws/growth-hacking"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/growth-hacking/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/san-npm/skills-ws/growth-hacking"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/growth-hacking.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 | $0.00065 | $0.06407 |
| Opus 5.5 | $0.00026 | $0.02563 |
| Sonnet 5.5 | $0.00013 | $0.01281 |
| Haiku 4.5 | $0.00006 | $0.00641 |
Grade A, and why
growth-hacking 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 2mo 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Growth Hacking
The orchestration layer for growth: pick the bottleneck, design an experiment, ship it, read the result honestly, compound the wins. This skill owns frameworks, loop economics, experiment design, instrumentation, and the guardrails that keep growth legal and non-manipulative. For deep execution it cross-links to siblings (do not duplicate them):
- Experiment statistics / sample size / sequential testing →
ab-testing - PLG mechanics, freemium tiering, self-serve revenue →
product-led-growth - Churn, cohort, health/engagement scoring, win-back →
retention-analytics - Referral program mechanics, payouts, partner tracking →
affiliate-marketing - GA4, attribution models, dashboards →
marketing-analytics - Welcome/nurture/winback email + bulk-sender compliance →
email-sequence - GDPR/ePrivacy/consent (EU) →
eu-legal-compliance
Golden rule: growth-hack the funnel, not the human. Every tactic below must be truthful, reversible, and something you'd be comfortable explaining to the user out loud. Manipulative dark patterns are out of scope and increasingly illegal (see Responsible Growth).
1. AARRR Framework (Pirate Metrics)
| Stage | Core metric | How to read it | Typical SaaS reference range* |
|---|---|---|---|
| Acquisition | New qualified signups / channel | Cost (CAC) and quality (downstream activation), not raw volume | Channel-dependent; judge by CAC payback < 12 mo |
| Activation | % reaching the aha action in first session/week | Define the single action correlated with retention | Self-serve B2C 20–40%; PLG B2B 30–50% |
| Retention | Cohort retention at the natural usage cadence | Look at the curve shape (does it flatten?), not one number | Varies wildly by category — see note below |
| Revenue | Free→paid conversion / expansion (NRR) | Separate new conversion from expansion | Freemium 2–5%; free-trial 10–25%; NRR target >100% |
| Referral | Viral coefficient K and referral share of new users | Decompose K (see §2) instead of trusting one number | K rarely >1 in practice; >0.4 is already strong |
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.
- 2mo ago First seen · 324 lines · 65 tokens per session scan A e630109e59be
growth-hacking is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 6,407 once invoked, about $0.0003 per session on Opus 5.5. 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.
growth-hacking compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| growth-hackingsan-npm/skills-ws | Skill | 4 | 1mo ago | MIT | A | 65 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |