See how it all connects.
Follow an idea into the model, a prediction into a decision, and a missed outcome back into research.
Atlanta at Green Bay · kickoff Sep 24 · 6:15 PM MT
Deliver stored predictions before kickoff · checked Sep 24 · 9:06 AM MT
Keep moving. Keep a reserve.
Jobs run from the Mac’s scheduler. This chat does not need to stay active.
Deferred work stays queued. Build jobs can use Claude or Codex according to available capacity. Gemini CLI starts are spaced at least 15 minutes apart after its hold expires; its remaining percentage is unknown.
How the guard works · last run: completed
Last supervisor receipt: Sep 24 · 8:57 PM MT. child exit 0
Codex starts are paced through the weekly window. Interactive usage also consumes that allowance. A missing or stale reading defers new work. Account reporting delay and in-flight usage mean the reserve is a control target, not an exact guarantee. A safety stop can leave partial edits requiring review.
Outstanding at the September 23 evening check: pinned forecast refresh errors, a red full-suite sweep, stale odds capture, a news-browser startup error and a grind input error. See Operations for newer evidence. Yahoo remains unresolved: both apps passed OAuth but Fantasy API requests returned 403.
103 of 128 marked done · counted once across the machine
Build progress counts items equally.
It does not estimate time or prediction accuracy.
Arrows show the architecture and intended handoffs, not live traffic. Plan completion is separate from runtime health and prediction accuracy. Snapshot Sep 24 · 10:41 PM MT. Select a component for its evidence.
Weekly model allowance
Claude
Read Sep 24 · 9:20 PM MT
Resets Oct 1 · 9:00 PM MT
Pace unavailable until a fresh weekly reading with a future reset.
Logged scheduled starts, past 24 hours: 0
Account-wide allowance; includes work outside Playerweek.
Usage endpoint could not be read on this refresh.
Codex
Read Sep 24 · 10:42 PM MT
Resets Oct 1 · 6:26 PM MT
Reset in 6.8 days (163.7 hours)
Current pace: 124.28% / day over 4.2 hours
Sustainable pace: 11.43% / day through reset
Logged scheduled starts, past 24 hours: 82
gpt-6-astra: 63 completed CLI runs in 24 hours · 89,748,995 recorded tokens across 63 runs (1,424,587 per run on average)
gpt-6-sol: 18 completed CLI runs in 24 hours · 27,619,423 recorded tokens across 18 runs (1,534,412 per run on average)
Run model and tokens come from Codex session metadata; account quota is shared across models. Per-model cost and quota draw are not reported.
Account-wide Codex allowance. Direct account-status read; no model request.
Antigravity · Gemini models
Read Sep 24 · 10:42 PM MT
Resets Oct 1 · 7:29 PM MT
Reset in 6.9 days (164.8 hours)
Current pace: 2.78% / day over 2.5 hours
Sustainable pace: 14.49% / day through reset
Logged scheduled starts, past 24 hours: 7
Shared by Gemini Flash and Pro in Antigravity. Local scheduled starts also have a 15-minute cooldown. Gemini app/web usage is unknown here.
Antigravity · Claude and GPT models
Read Sep 24 · 10:42 PM MT
Resets Oct 1 · 10:42 PM MT
Reset in 7.0 days (168 hours)
Current pace: unknown; need two readings at least 30 minutes apart in this reset window.
Sustainable pace: 14.29% / day through reset
Scheduled starts: no local ledger for this allowance
Shared by Claude Opus, Claude Sonnet and GPT-OSS in Antigravity; separate from Claude Code and Codex.