pm-studio: Agent for Claude Code

.claude/agents/metrics-designer.md

Metrics Designer is an agent for Claude Code from zoekdestep/pm-studio. It costs 14 tokens per session (738 once invoked), scanned A, original, MIT.

An agent that reviews how a product or project measures success and suggests better metrics. It covers targets, starting points, actionability, and ways teams might reach a number without delivering real value.

In plain words
What is it for?
Use it to assess existing metrics and suggest primary measures such as activation, engagement, outcomes, and retention, plus guardrails that should not get worse.
Why use it?
It helps turn vague or misleading success measures into clearer measures tied to user and business outcomes.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is zoekdestep/pm-studio's own configuration. It tells Claude Code how to work on pm-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pm-studio configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/zoekdestep/pm-studio/main/.claude/agents/metrics-designer.md
Clone the repo
git clone --depth 1 https://github.com/zoekdestep/pm-studio

Made for: Claude Code.

Wrote 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.

agentmods badge for Metrics Designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zoekdestep/pm-studio/metrics-designer.svg)](https://agentmods.dev/agents/zoekdestep/pm-studio/metrics-designer)
Your own site
<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>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 8c4625b2b8d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.claude/agents/metrics-designer.md · 101 lines

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]

Read the full file on GitHub · 101 lines

Changes

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.

  1. 8d ago First seen · 101 lines · 14 tokens per session scan A 8c4625b2b8d5

Subscribe to this mod's changes

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.