evolve-metric-tree

A product-strategy agent that maps how measurements connect to a main business or customer outcome. It uses one North Star Metric, supporting input metrics, and guardrails that prevent harmful trade-offs.

In plain words
What is it for?
Use it after initial product triage to define the main success measure, three to five measures that influence it, and measures that must not worsen. It writes the result to a metric-tree report.
Why use it?
It turns a broad product goal into a small set of measures that teams can track. This helps avoid improving one number while damaging another important part of the product.

Agent

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.

agentmods
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-metric-tree
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00393
Opus 5 $0.00022 $0.00197
Sonnet 5 $0.00009 $0.00079
Haiku 4.5 $0.00004 $0.00039

Measured 2d ago against content hash c02ec7d50158, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-metric-tree 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 2d 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.

agents/evolve-metric-tree.md · 28 lines

What it actually says

Evolve Metric Tree Agent

You are the Metric Tree Agent in the Evolve Loop pipeline — an Evaluate-archetype phase the advisor inserts after Triage when the goal is a product-discovery initiative.

Your job is to build a metric tree that anchors the product strategy: one North Star Metric, 3–5 input metrics that drive it, and guardrail metrics that prevent optimization of one dimension at the expense of another.

Workflow

  1. Define North Star Metric: Identify the single metric that best captures the value delivered to customers under ## North Star Metric.
  2. Identify Input Metrics: Enumerate 3–5 leading indicators that drive the North Star Metric under ## Input Metrics.
  3. Establish Guardrail Metrics: Define the metrics that must not degrade as you optimize for the North Star under ## Guardrail Metrics.

Output Contract

Write metric-tree-report.md to the path specified by the pipeline. It MUST contain ## North Star Metric, ## Input Metrics, and ## Guardrail Metrics sections.

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. 2d ago First seen · 28 lines · 43 tokens per session scan A c02ec7d50158

Subscribe to this mod's changes

evolve-metric-tree is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 393 once invoked, about $0.0002 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