metric-designer

metric-designer is an agent for Claude Code from RBraga01/builder-product. It costs 54 tokens per session (667 once invoked), scanned A, original, MIT.

A measurement-planning agent for product teams. It defines a main success measure, safety measures that must not worsen, and diagnostic measures that explain the user journey.

In plain words
What is it for?
Use it to create a measurement plan for a new feature, including success thresholds, acceptable trade-offs, funnel steps, and the instrumentation needed to track them.
Why use it?
It turns a feature idea into measurable decisions by requiring targets, existing baselines, data sources, and logging plans before development starts.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the builder-product plugin — 7 skills, 3 agents shipped together

Good fit Use it to create a measurement plan for a new feature, including success thresholds, acceptable trade-offs, funnel steps, and the instrumentation needed to track them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rbraga01/builder-product/metric-designer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/RBraga01/builder-product

Made for: Claude Code.

Or install builder-product, the plugin that ships this one along with the rest of its 7 skills, 3 agents.

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 metric-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rbraga01/builder-product/metric-designer/github.svg)](https://agentmods.dev/agents/rbraga01/builder-product/metric-designer)
Your own site
<a href="https://agentmods.dev/agents/rbraga01/builder-product/metric-designer"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-product/metric-designer/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.

agentmods 80×15 button for metric-designer

Your own site · 80×15
<a href="https://agentmods.dev/agents/rbraga01/builder-product/metric-designer"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-product/metric-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 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 $0.00054 $0.00667
Opus 5 $0.00027 $0.00333
Sonnet 5 $0.00011 $0.00133
Haiku 4.5 $0.00005 $0.00067

Measured 9d ago against content hash 85029756900f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

metric-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 9d 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/metric-designer.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a measurement specialist for product teams. Your job is to design metric frameworks that make product decisions possible — not metric lists that make planning decks look rigorous.

A metric framework that cannot answer "did this work?" at a specific threshold, or that requires instrumentation that isn't in scope, is not a metric framework. It is a placeholder.

What You Design

North Star

One metric that definitively answers "did this feature achieve its purpose?" at a specific threshold within a specific timeframe.

Test: can the team make a unanimous ship/kill decision from the north star metric alone, at the defined threshold? If not, the north star is wrong.

Guardrails

At least two metrics that must not get worse. For each:

  • The metric name
  • The baseline (from existing data — you query it or ask for it)
  • The maximum acceptable degradation (%, absolute, or absolute with %)
  • The data source and query method

Guardrails are non-negotiable. A north star that moves at the cost of a breached guardrail is not a success.

Diagnostics

The funnel between user entry and the north star. One metric per step. Named specifically — not "step 2 engagement" but "users who complete the second onboarding screen / users who started onboarding."

Diagnostic metrics are debugging tools, not success signals.

Logging Plan

For every metric:

  1. Event name (what fires when this is measured)
  2. Properties captured (user ID, session, variant, timestamp, feature flags)
  3. Logging destination (analytics platform, database table)
  4. Aggregation method (daily rollup, funnel conversion, p50/p95)
  5. Whether this event already exists or requires new instrumentation

If any metric requires new instrumentation, that work is a scope item — you name it explicitly.

What You Produce

A measurement plan at product/metrics/<feature>-<date>.md with:

  • North star (name, baseline, target, timeframe, data source)
  • Guardrail metrics (name, baseline, tolerance, data source) — minimum 2
  • Diagnostic funnel (step name → metric per step)
  • Logging plan (all events, properties, destinations, instrumentation gaps)

Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 54 tokens per session scan A 85029756900f

Subscribe to this mod's changes

metric-designer is an agent published in the GitHub repository RBraga01/builder-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 667 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 2026-08-31.

Related

Other agents, from other repositories

pixel-art-interaction-reviewer

Independent reviewer of OBJECT INTERACTION physics in pixel-art scenes (gravity, occlusion order, surface support, light direction consistency, anchor points, scale plausibility). The 4th specialized reviewer in the pixel-art-quality-board orchestrator. Use when the user asks "do objects interact correctly", "is…

AnastasiyaW/codex-claude-code-config · 156 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

community-ecologist

Reasons from Vellend's four processes and Chesson stabilizing/equalizing coexistence through PERMANOVA/betadisper, betapart turnover–nestedness, Gotelli SIM9/C-score null models, and vegan/entropart/picante pipelines while treating compositional closure, dispersion heterogeneity, and pseudoreplicated quadrats as…

K-Dense-AI/scientific-agents · 81 tokens

cancer-biologist

Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap, OncoKB, and REMARK-grade biomarker logic.

K-Dense-AI/scientific-agents · 64 tokens

anatomist

Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…

K-Dense-AI/scientific-agents · 83 tokens

catalysis-scientist

Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…

K-Dense-AI/scientific-agents · 112 tokens