Skip to content

Metrics Dashboard

Live rollup of metrics from instrumentation/daily-log.md.

Current window

  • Window: set when first baseline is captured
  • Tasks logged: 0
  • Median lead time:
  • Median switches/task:
  • Rework rate:
  • Median friction:

30-day exit-criteria scoreboard

(See plan §"30-Day Exit Criteria". Each row updated weekly.)

Criterion Status Evidence
Repeatable default loop in most coding sessions not started
≥ 1 MCP integration reducing context switching not started
Subagent + skill set stable and reused not started
Review workflow catches real issues with acceptable noise not started
Production-usable skill-factory flow not started
New projects bootstrap rules from global baseline not started
AnyType PKM + agent wiki operating with privacy boundaries not started
Intelligent handoff protocol with measurable readiness thresholds not started
Governance artifacts sufficient for one auditable promotion dry run not started
Adversarial sandbox: one authorized scan→fix→retest loop not started
Docs/publish pipeline: multi-format outputs with policy-gated publish not started