# Meter Compare

Compare CocoMeter accuracy and cost results with correctness-first ordering.

- Repository: https://github.com/Snowflake-Labs/cocoplus (727 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-04
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Snowflake-Labs/cocoplus --skill meter-compare -g -a claude-code -y`
Codex: `npx skills add Snowflake-Labs/cocoplus --skill meter-compare -g -a codex -y`
Cursor: `npx skills add Snowflake-Labs/cocoplus --skill meter-compare -g -a cursor -y`
Gemini CLI: `npx skills add Snowflake-Labs/cocoplus --skill meter-compare -g -a gemini-cli -y`

## Description

Compare CocoMeter accuracy and cost results with correctness-first ordering. Usage: $meter compare <before.json> <after.json>.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

Use this skill for `$meter compare`.

## Objective

Compare two CocoMeter or harness benchmark result files while respecting the configured optimization objective. The default is correctness-first: accuracy delta is the primary signal and token/cost delta is secondary.

CocoMeter session summaries may include three named cost rows:
- `execution_cost`: functional stage work.
- `coordination_cost`: advisor calls, handoff context assembly, artifact transfer, and status sync.
- `landing_cost`: reserve-window spend for final evaluation, console update, and handoff.

When `[meter] track_acrr = true`, session summaries may also include:
- `acrr_this_session`: average Agent Cognitive Redundancy Ratio across completed CocoFlow runs in the session.
- `acrr_runs[]`: the last run-level records with `complexity_tier_estimated`, `model_tier_configured`, `model_tier_actual`, `model_tier_used`, `model_drift`, `escalations_taken`, and `acrr`.

When `[meter] meter_reconciliation_enabled = true`, finalized session summaries may include `reconciliation_status`, `metering_gap_fraction`, `duplicates_found`, `model_tier_configured`, `model_tier_actual`, and `model_drift`. Treat transcript-derived totals as authoritative for billing comparisons when `reconciliation_status` is `gap_corrected`.

Treat ACRR as a calibration diagnostic, not an accuracy score. ACRR near 1.0 indicates that the initial complexity tier was sufficient. Consistently high ACRR indicates the task class is being underestimated before dispatch.

## Workflow

The rest: https://github.com/Snowflake-Labs/cocoplus/blob/HEAD/.cortex/skills/cocometer/meter-compare/SKILL.md