← charleslikesdata.com afk cockpit
6 repos · 929 runs · 759 issues · 661 merged · data through Jun 7 – Aug 1, 2026

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.
98%
landed rate
n = 673 gate-passed
98%
landed rate (executor repos)
n = 6 exec repos
$3.92
API-equiv $ / merged PR
n = 661 merged
fully loaded: includes failed runs, quarantines, and scout overhead
35%
quarantine (safety) rate
n = 759 issues
19%
escalation rate
n = 929 runs
0%
rejected rate
n = 1,247 proposals
Pipeline

Stage funnel

proposed
1,247
promoted
766
61% of proposed
attempted
759
99% of promoted
passed gate
673
89% of attempted
published
662
98% of passed gate
merged
661
100% of published
By repository

Outcomes per repo

landed quarantined other
Orbit-Wars
75 · 87%
afk-agent-system
403 · 89%
afk-cockpit
106 · 94%
household-bms
48 · 96%
the-vault
11 · 0%
the-workshop
116 · 79%
Producers

Proposal quality

dropped
243
harvest
5
mis-sized
54
pending
177
rejected
1
shipped
766
superseded
1
Safety axis

Quarantine by category

266 total
other
83
no-op
41
capability
22
review
22
integration-conflict
17
build-crash
16
scope
11
setup-crash
10
test-conflict
8
circuit-breaker
7
deny-surface
7
timeout
6
coupling
4
idle-timeout
4
unrecoverable-signature
3
flaky-test
2
security
2
environmental
1
Retries & recovery

Runs per issue

1.22 avg runs/issue
12345
Retries & recovery

Quarantine → retry rescue

retry rescues 57% of first-run quarantines · 99% of those actually retried
73%
first-try pass rate
17%
final-state quarantine (issues)
29%
quarantine rate (runs)
Cost · API-equivalent
fleet telemetry · per attempt · Jun 7 – Aug 1, 2026

Spend by model tier

$2,293.58 total across the window
sonnet$1418.64 · avg $1.59/attempt · n=894 attempts
unknown tier$674.64 · avg $1.69/attempt · n=399 attempts
opus$200.31 · avg $2.47/attempt · n=81 attempts
⚠ 29% of attempt spend ($674.64 · 399 attempts) has no recorded model_tier — telemetry gap, not a model
Overhead · orchestrator + scout ops
$294.81
243 cost events · additive to the tier spend above · not a model tier
Claude Code transcripts, afk worktrees only · per API call · Jul 2 – Aug 1, 2026
$0.03
median / call
$0.07
p90 / call
33,876
calls logged
whole machine, all projects: $8,743.31 across 70,245 calls
Cost dial

Per-API-call cost distribution

26613
6031
919
197
92
19
5
<$.05.05–.10.10–.15.15–.20.20–.30.30–.50$.50+
Model mix

Opus share by day

Jul 2 range: 0%–62% Aug 1
Throughput

Slices per day

929 runs
06-0706-1306-1906-2707-0307-1407-2307-30
Context cost

Tokens by type, per day

2.40B tokens · 95.8% cache reads — the context is overwhelmingly cached
cache read cache write input output