Skip to content

Commander Maturity Scoring — Meruem's Assessment Framework ​

Per-commander score (0–100, five dimensions × 20) ​

Dimension0 (dead)10 (functional)20 (thriving)
Context healthMissing/stubHas scope but stale >30dComplete, updated <14d, links resolve
Output volumeZero government files1–3 files, some stubs4+ substantive files, recent
Initiative pipelineNo initiatives sectionProposed but not shippedShipped and producing value
Goal alignmentNo active project linkIndirect alignmentDirect alignment to top-3 project
Token efficiencyHigh burn, zero outputModerate burn, some outputCost justified by output

Bands ​

BandScoreMeaning
THRIVING80–100Commander is actively compounding Michael's growth
ACTIVE60–79Commander is functional and producing
DORMANT40–59Commander exists but not producing value
STALLED20–39Commander needs intervention or dissolution
DEAD0–19Dissolution candidate

Federation-level metrics ​

MetricDefinition
VitalityMean maturity score across all commanders
Coverage ratioActive projects (CLAUDE.md) with at least one ACTIVE+ commander
Drift indexBand drops since last assessment
Growth velocityBand gains since last assessment

Assessment cadence ​

  • Fortnightly (1st + 15th) — full sweep, all commanders, all 5 dimensions
  • On-demand — single commander or pillar, when triggered by structural change
  • Post-dissolution — re-score affected pillar

Input signals ​

  1. Context file health — federation/*.md modification dates via git log
  2. Government output trail — file count in the-government/ per commander domain
  3. Delegation initiative pipeline — YAML from context files, proposed→shipped velocity
  4. Token burn data — orochimaru.token_burn_agents (Z2 postgres)
  5. Git commit trail — git log --since="14 days ago" across federation/, the-government/, supreme-court/
  6. Goal alignment — cross-reference against CLAUDE.md Active Projects

Output artifacts ​

ArtifactPathConsumer
Evolution assessmentthe-government/information_reference/reference_evolution-assessment-YYYY-MM-DD.mdMichael, Orochimaru
Maturity score JSONStudio public/data/maturity-scores.json (schema TBD)Studio MaturityTimeline
Telegram summaryOne-paragraph federation health pushMichael

Relationship to other KPIs ​

  • Delegation thresholds (delegation-thresholds) measure session-level work distribution
  • Maturity scoring measures commander-level contribution over 14-day cycles
  • Token burn (Orochimaru) feeds the token efficiency dimension
  • Maturity scores feed Orochimaru's model-ladder tier assignments

Meruem owns scoring. Toph (lieutenant) verifies input signals before scores are issued.