Autonomous-PR outcomes across the fleet. Cost is API-equivalent (notional on a Pro subscription). Quarantines are a safety signal — afk refused to ship — not failures.
Fleet state · not yet wired up
Live gate/promote/merge and dependency-frontier state isn't ingested
yet — this panel is a placeholder for a future feature, not a
fabricated number.
99%
landed rate
n = 500 gate-passed
99%
landed rate (executor repos)
n = 5 exec repos
excludes my-brain (10 quar)
$3.52
API-equiv $ / merged PR
n = 495 merged
fully loaded: includes failed runs, quarantines, and scout overhead
37%
quarantine (safety) rate
n = 568 issues
21%
escalation rate
n = 702 runs
0%
rejected rate
n = 837 proposals
Pipeline
Stage funnel
By repository
Outcomes per repo
landed
quarantined
other
Orbit-Wars
51 · 98%
afk-agent-system
293 · 99%
afk-cockpit
91 · 99%
claude-workflow
75 · 98%
household-bms
48 · 100%
my-brain
10 · 0%
Producers
Proposal quality
Safety axis
Quarantine by category
Retries & recovery
Runs per issue
12345
Retries & recovery
Quarantine → retry rescue
retry rescues 58% of first-run quarantines · 98% of those actually retried
71%
first-try pass rate
17%
final-state quarantine (issues)
30%
quarantine rate (runs)
Cost · API-equivalent
fleet telemetry · per attempt · —
Spend by model tier
$1,601.47 total across the window
Claude Code transcripts, afk worktrees only · per API call · —
$0.03
median / call
$0.08
p90 / call
47,244
calls logged
whole machine, all projects: $6,232.82 across 68,626 calls
Cost dial
Per-API-call cost distribution
<$.05.05–.10.10–.15.15–.20.20–.30.30–.50$.50+
Model mix
Opus share by day
no data yet
Throughput
Slices per day
no data yet
Context cost
Tokens by type, per day
cache read
cache write
input
output
no data yet