v1v2
role
trust
Queue
TOKENS MTD
31.4B tokens
RECOVERABLE
5.5B tokens/mo17.7%
BANKED MTD
1.6B tokensrealized
Δ VS JUN PACE
+3.2%

Your Sonnet downshift for Checkout (acted Jun 28) is tracking 107% of projection.

778M tokens/mo realized vs 725M tokens projected
Ledger →
top move· HIGH · realizes 87% historically

Route 2,800 trivial Opus sessions to Sonnet across Checkout & DevEx

2.1B tokens/moPOLICYMEASURED

why · Rule ‘model over-provisioning’ fired: 2,800 sessions in 30d were ≤6 min, ≤10 tool calls, ≥85% acceptance — Opus adds no measurable quality on these.

better · Adopt a default-model policy: trivial edits start on Sonnet/Haiku, escalate only on failure. Ship the routing note and fold it into the onboarding playbook.

POLICYAdmin · one config changeSet policy

Org cache hit 61% vs 75% target — worst offender SRE Core at 58%

COACHINGMEASURED975M tokens/mo

14 stranded seats — activated, idle 30+ days

295M tokens of allowance leaked since posted 12d ago
POLICYMEASURED735M tokens/mo

Checkout runs 1,525,000 tokens per accepted diff vs 960,000 tokens org median — driver: model mix

PROXY+59% tokens/diff

9 dangerous-command overrides on prod-adjacent repos this week — Sam Doyle, Leo Rao +2

MEASURED9 overrides

Vendor Pod Chennai — Rahul M., Arjun K. +3: 120 Opus sessions on trivial tasks

POLICYMEASURED438M tokens/mo

Cleared this week: 9 moves → 2.0B tokens/mo projected (verification running on 4)

Compiled 07:30 from 1,204 sessions · quota weight table v3 (May 12) · measured vs proxy tagged · Accountability-focused