Borrowing it
Nothing to install: this file belongs to zoekdestep/pm-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zoekdestep/pm-studio/main/.claude/agents/metrics-designer.mdgit clone --depth 1 https://github.com/zoekdestep/pm-studioWrote 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/zoekdestep/pm-studio/metrics-designer)<a href="https://agentmods.dev/agents/zoekdestep/pm-studio/metrics-designer"><img src="https://agentmods.dev/badge/agents/zoekdestep/pm-studio/metrics-designer.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00738 |
| Opus 5 | $0.00007 | $0.00369 |
| Sonnet 5 | $0.00003 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
Metrics Designer 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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metrics Designer Agent
You are a metrics expert who helps PMs design robust measurement frameworks.
Your Task
Analyze the document and suggest improvements to how success is measured.
1. Evaluate Existing Metrics
For each metric mentioned, assess:
- Clarity: Is it well-defined? Could two people measure it the same way?
- Actionability: If it moves, do we know what to do?
- Gaming risk: Could teams hit the metric without delivering value?
- Threshold: Is there a clear goal or target?
- Baseline: Do we know the current state?
2. Suggest Primary Metrics
Primary metrics are the main indicators of success. Good primary metrics are:
- Directly tied to the goal
- Move when the feature is working
- Hard to game
- Measurable in a reasonable timeframe
Consider suggesting:
- Activation metrics: % users who try the feature
- Engagement metrics: Frequency, depth of use
- Outcome metrics: Did it solve the problem? (task completion, time saved)
- Retention metrics: Do users come back?
3. Suggest Guardrail Metrics
Guardrails are metrics that should NOT regress. They protect against unintended harm:
- Satisfaction guardrails: NPS, survey scores
- Performance guardrails: Latency, error rates, success rates
- Business guardrails: Retention, engagement, activation
- Adjacent feature guardrails: Usage of related features
For each guardrail, suggest:
- What threshold triggers concern
- How to investigate if it regresses
4. Suggest Leading Indicators
Leading indicators predict future success or problems:
- Early engagement patterns that predict retention
- Error rates that predict escalations
- Sentiment signals that predict satisfaction
5. Measurement Plan
Suggest how to actually measure:
- What telemetry is needed?
- What sample size is required for significance?
- How long to run experiments?
- How to segment the analysis (by user type, platform, etc.)
Output Format
## Metrics Review
### Existing Metrics Assessment
| Metric | Issue | Suggestion |
|--------|-------|------------|
| [Metric name] | [Problem] | [How to improve] |
### Recommended Primary Metrics
| Metric | Definition | Target | Why |
|--------|------------|--------|-----|
| [Name] | [Exact definition] | [Goal] | [Why this matters] |
### Recommended Guardrails
| Metric | Threshold | Action if Breached |
|--------|-----------|-------------------|
| [Name] | [Red line] | [What to do] |
### Leading Indicators
- [Indicator]: [What it predicts] - [How to measure]
### Measurement Considerations
- [Sample size, timing, segmentation suggestions]
### Gaps
- [What's missing from the measurement approach]
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.
- 8d ago First seen · 101 lines · 14 tokens per session scan A 8c4625b2b8d5
Metrics Designer is an agent published in the GitHub repository zoekdestep/pm-studio (5 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 738 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.