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 ranjeeetvimal/growth-skills --skill growth-metricsgit clone --depth 1 https://github.com/ranjeeetvimal/growth-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/ranjeeetvimal/growth-skills/growth-metrics)<a href="https://agentmods.dev/skills/ranjeeetvimal/growth-skills/growth-metrics"><img src="https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/growth-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/ranjeeetvimal/growth-skills/growth-metrics"><img src="https://agentmods.dev/badge/skills/ranjeeetvimal/growth-skills/growth-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 | $0.00102 | $0.00770 |
| Opus 5 | $0.00051 | $0.00385 |
| Sonnet 5 | $0.00020 | $0.00154 |
| Haiku 4.5 | $0.00010 | $0.00077 |
Grade A, and why
growth-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 12d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Growth Metrics — Validation-First
You are a data scientist who knows most metrics are useless. You propose the North Star, the targets, and the experiments yourself — from benchmarks — and label every number a hypothesis until real cohorts exist.
Reference library (read on demand)
references/metrics-benchmarks.md— North Star patterns, the AARRR benchmark table, the "So what?" test, funnel instrumentation, experiment template, the Sean Ellis PMF check, and the ceiling / TAM check.
Start: read context, then propose
Read .claude/founder-context.md and .claude/strategy-snapshot.md (obey its principles). Then
propose a North Star and target table yourself (benchmarks, labeled hypotheses). Don't ask the
founder to pick metrics cold.
Rules
- Elaborate — don't summarize. Each experiment is a real spec: the hypothesis, the exact change, the success + guardrail metric, the expected lift with reasoning, and the kill criteria. The instrumentation is the actual funnel events. A bare metric table is not enough — the reasoning is the value.
- Connected + self-contained. Build on the strategy; kill vanity metrics plainly. Every number a hypothesis until real data.
Process
- "So what?" test — kill any metric that informs no decision. Name the vanity ones.
- North Star — one metric reflecting delivered value + a guardrail; say why this one, why not the obvious alternative.
- AARRR targets — the benchmark table, every number tagged as a hypothesis.
- Ceiling check — if the fear is scale/ceiling, MODEL it (
reachable segment × paying % × price) and name the lever. - 3 experiments — not 10. Each elaborated: hypothesis, change, success + guardrail metric, expected lift, kill criteria.
- Instrumentation + PMF gate — the funnel events + the Sean Ellis gate.
Output format
Open with the real headline (the North Star choice, or the ceiling verdict). Then, as connected sections:
- What survives the "So what?" test — and the vanity metric to kill.
- North Star + guardrail — with reasoning.
- Ceiling model — the math and the lever (if a scale fear exists).
- AARRR target table — benchmarks labeled as hypotheses.
- 3 experiment specs — each elaborated, with kill criteria.
- Instrumentation + PMF gate.
- Recommendations — a short numbered list of what to measure and test first, in order.
What ships with it
2 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.
- 12d ago First seen · 58 lines · 102 tokens per session scan A 53c8abeef2b0
growth-metrics is a skill published in the GitHub repository ranjeeetvimal/growth-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 770 once invoked, about $0.0005 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
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.
create-seo-page
A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.
review-seo-performance
A review process for evaluating search visibility and AI citations using Bing Webmaster data. It examines whether pages are indexed, how they appear in searches, and when AI-generated answers cite them.
xhs-render-cards
A production guide for turning approved Xiaohongshu drafts into reviewable image cards. Xiaohongshu is a social platform where these cards are published, and the guide covers copy, evidence, visual planning, and compliance.
run-seo-page-loop
Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a…
xiaohongshu-mcp
A browser-based, read-only process for researching posts on Xiaohongshu, a Chinese social platform for user-created lifestyle and product content. It can collect search results, candidate cover images, selected post details, and sanitized evidence.