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 uthumany/uthy-legacy-os --skill metrics-frameworkgit clone --depth 1 https://github.com/uthumany/uthy-legacy-osWrote 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/uthumany/uthy-legacy-os/metrics-framework)<a href="https://agentmods.dev/skills/uthumany/uthy-legacy-os/metrics-framework"><img src="https://agentmods.dev/badge/skills/uthumany/uthy-legacy-os/metrics-framework/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/uthumany/uthy-legacy-os/metrics-framework"><img src="https://agentmods.dev/badge/skills/uthumany/uthy-legacy-os/metrics-framework.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 | $0.00028 | $0.00857 |
| Opus 5.5 | $0.00011 | $0.00343 |
| Sonnet 5.5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
metrics-framework 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metrics Framework
Overview
A metrics framework connects what you build to what matters. Without one, teams optimize for whatever number is loudest. This skill covers AARRR (Pirate Metrics), HEART (Google), and custom metric trees — choose the right framework and build a measurement system that drives decisions.
When to Use
- Defining success for a new product or feature
- Building or redesigning your analytics system
- Aligning the team around a shared measurement model
- Moving from vanity metrics to actionable metrics
- Don't use for: one-time analysis (use experiment-analysis skill), daily monitoring (use dashboard-design)
Instructions
1. Choose a Framework
AARRR (Pirate Metrics) — best for growth-stage products:
- Acquisition: How do users find you? (traffic sources, signups)
- Activation: Do users have a great first experience? (aha moment, time-to-value)
- Retention: Do users come back? (D1/D7/D30 retention, churn)
- Revenue: Do users pay? (MRR, ARPU, conversion rate)
- Referral: Do users tell others? (viral coefficient, NPS)
HEART (Google) — best for UX and engagement-focused products:
- Happiness: User satisfaction (NPS, CSAT, satisfaction surveys)
- Engagement: Frequency and depth of use (sessions, actions per session)
- Adoption: New users of a feature (onboarding completion, feature activation)
- Retention: Returning users (cohort retention, churn rate)
- Task Success: Can users accomplish goals? (success rate, time-on-task, errors)
Custom Metric Tree — best for complex or unique products:
- Start with a North Star metric
- Break down into 3-5 supporting drivers
- Each driver has leading and lagging indicators
- Each indicator has a target and owner
2. Define Metrics Hierarchy
North Star: One metric that captures the core value your product delivers. Input metrics: Actions users take that drive the North Star (controllable). Output metrics: Results of those actions (lagging). Counter-metrics: What should NOT degrade while you optimize.
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 · 88 lines · 28 tokens per session scan A 2de2dc9b2802
metrics-framework is a skill published in the GitHub repository uthumany/uthy-legacy-os (5 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 857 once invoked, about $0.0001 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.
metrics-framework compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| metrics-frameworkuthumany/uthy-legacy-os | Skill | 5 | 5mo ago | MIT | A | 28 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |