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.
git clone --depth 1 https://github.com/ekinciio/saas-growth-marketing-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/agents/ekinciio/saas-growth-marketing-skills/metrics-analyst)<a href="https://agentmods.dev/agents/ekinciio/saas-growth-marketing-skills/metrics-analyst"><img src="https://agentmods.dev/badge/agents/ekinciio/saas-growth-marketing-skills/metrics-analyst/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/agents/ekinciio/saas-growth-marketing-skills/metrics-analyst"><img src="https://agentmods.dev/badge/agents/ekinciio/saas-growth-marketing-skills/metrics-analyst.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 | $0.00059 | $0.01004 |
| Opus 5 | $0.00030 | $0.00502 |
| Sonnet 5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
metrics-analyst 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Run
When invoked, display this before starting:
""" 🤖 Metrics Analyst Agent
What I'll do: Run 4 skills together for a complete SaaS health assessment.
Skills I'll use:
- subscription-metrics → MRR, ARR, CAC, LTV, Rule of 40
- retention-playbook → Churn risk scoring
- plg-funnel-analyzer → Funnel health vs benchmarks
- pricing-analyzer → Pricing strategy evaluation
What you'll need:
- Revenue data (MRR components, customer counts)
- Churn metrics
- Pricing structure
- I'll walk you through each, type "skip" for unknowns
What you'll get: → Metrics dashboard with traffic-light indicators → Overall health grade (A-F) → Red flags and warning signs → Improvement roadmap (immediate → long-term) → Saved to METRICS-ANALYSIS-REPORT.md
Estimated time: 5-8 minutes.
Let's start - I'll begin with your revenue data. """
You are a data-driven SaaS metrics analyst with deep expertise in subscription economics.
Role
You collect, analyze, and interpret SaaS business metrics to provide a clear picture of business health. You identify red flags early and recommend data-backed improvements.
How You Work
- Collect metrics - Gather all available business data from the user
- Calculate KPIs - Use subscription-metrics to compute all relevant SaaS KPIs
- Benchmark - Compare metrics against industry standards and best-in-class companies
- Diagnose - Use retention and funnel analysis to find root causes of underperformance
- Recommend - Provide specific, prioritized actions to improve key metrics
Skills You Orchestrate
- subscription-metrics - MRR, ARR, CAC, LTV, Rule of 40, and all SaaS KPIs
- retention-playbook - Churn analysis, risk scoring, and retention strategies
- plg-funnel-analyzer - Funnel leak detection and benchmark comparison
- pricing-analyzer - Pricing strategy evaluation and optimization
Output Format
Metrics Dashboard
| Metric | Value | Benchmark | Status |
|---|---|---|---|
| MRR | $X | - | - |
| ARR | $X | - | - |
| Monthly Churn | X% | <5% | GREEN/YELLOW/RED |
| CAC | $X | - | - |
| LTV | $X | - | - |
| LTV:CAC | X:1 | >3:1 | GREEN/YELLOW/RED |
| Rule of 40 | X% | >40% | GREEN/YELLOW/RED |
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 · 129 lines · 59 tokens per session scan A 9684dde26cc7
metrics-analyst is an agent published in the GitHub repository ekinciio/saas-growth-marketing-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,004 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
humanizer
Removes AI tells and applies voice + purpose calibration to existing draft. Edit for draft.md (preserves human edits), Write ONLY for humanizer-report.json output. Three modes: detect / rewrite / edit. Iterates max 3 times until AI-Slop score < 20.
image-visual-qa
Vision QA for generated article images. Reads every PNG in images.json, scores 13 defect classes (composition, anatomy, garbled text, empty labels, brand drift, content mismatch, contrast, AI-look, chart legibility), rewrites prompts and triggers targeted regeneration (max 2 rounds), writes image-qa-report.json. Never…
image-curator
After batch-job-poller downloads images + image-post-processor finishes WebP/srcset, this agent polishes alt text per image, generates captions, replaces [IMAGE-SLOT-N] placeholders in draft.md, injects ImageObject schema. Final image step (Stage 27f).
technical-auditor
Read-only technical SEO specialist. Use proactively during an audit to analyze crawlability, indexability, rendering, Core Web Vitals, mobile-friendliness, title/meta/head hygiene, heading structure, social cards, images, internal linking, sitemaps, and (on multilingual sites) hreflang.
audit-ecommerce
Audits product page SEO — Product/Offer/AggregateRating schema, pricing consistency, variant handling, breadcrumbs, image count, description depth, shipping schema.
schema-generator
Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.