← charleslikesdata.com afk cockpit
11 repos · 1,228 runs · 1,013 issues · 903 merged · data through Jun 7 – Aug 31, 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 = 925 gate-passed
98%
landed rate (executor repos)
n = 11 exec repos
$4.11
API-equiv $ / merged PR
n = 903 merged
fully loaded: includes failed runs, quarantines, and scout overhead
32%
quarantine (safety) rate
n = 1,013 issues
18%
escalation rate
n = 1,228 runs
0%
rejected rate
n = 1,282 proposals
Pipeline

Stage funnel

proposed
1,282
promoted
376
29% of proposed
attempted
1,013
269% of promoted
passed gate
925
91% of attempted
published
909
98% of passed gate
merged
903
99% of published
By repository

Outcomes per repo

landed quarantined other
Orbit-Wars
127 · 89%
afk-agent-system
502 · 90%
afk-cockpit
106 · 94%
breakroom
37 · 84%
graphmark
15 · 93%
household-bms
52 · 92%
household-command-center
2 · 50%
housing-commute-analysis
15 · 93%
kaggriculture
22 · 91%
ragmark
9 · 89%
the-workshop
126 · 80%
Producers

Proposal quality

dropped
69
mis-sized
116
pending
720
rejected
1
shipped
376
Safety axis

Quarantine by category

322 total
other
86
no-op
46
review
30
scope
29
capability
22
integration-conflict
20
build-crash
17
deny-surface
13
setup-crash
10
test-conflict
10
timeout
8
circuit-breaker
7
auth
4
coupling
4
environmental
4
idle-timeout
4
unrecoverable-signature
3
flaky-test
2
security
2
rate-limit
1
Retries & recovery

Runs per issue

1.21 avg runs/issue
12345
Retries & recovery

Quarantine → retry rescue

retry rescues 63% of first-run quarantines · 108% of those actually retried
75%
first-try pass rate
15%
final-state quarantine (issues)
26%
quarantine rate (runs)
Cost · API-equivalent
fleet telemetry · per attempt · Jun 7 – Aug 31, 2026

Spend by model tier

$3,053.71 total across the window
sonnet$2082.58 · avg $1.71/attempt · n=1219 attempts
unknown tier$670.16 · avg $1.69/attempt · n=397 attempts
opus$300.97 · avg $2.47/attempt · n=122 attempts
⚠ 22% of attempt spend ($670.16 · 397 attempts) has no recorded model_tier — telemetry gap, not a model
Overhead · orchestrator + scout ops
$657.00
658 cost events · additive to the tier spend above · not a model tier
Claude Code transcripts, afk worktrees only · per API call · Aug 1 – Aug 31, 2026
$0.04
median / call
$0.10
p90 / call
10,598
calls logged
whole machine, all projects: $6,398.19 across 42,326 calls
Cost dial

Per-API-call cost distribution

6390
3022
760
253
134
35
4
<$.05.05–.10.10–.15.15–.20.20–.30.30–.50$.50+
Model mix

Opus share by day

Aug 1 range: 0%–70% Aug 31
Throughput

Slices per day

1,228 runs
06-0706-1606-2707-0607-2308-0208-1108-20
Context cost

Tokens by type, per day

913.8M tokens · 96.4% cache reads — the context is overwhelmingly cached
cache read cache write input output