← charleslikesdata.com afk cockpit
9 repos · 1,017 runs · 837 issues · 741 merged · data through Jun 7 – Aug 4, 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 = 753 gate-passed
98%
landed rate (executor repos)
n = 9 exec repos
$3.93
API-equiv $ / merged PR
n = 741 merged
fully loaded: includes failed runs, quarantines, and scout overhead
33%
quarantine (safety) rate
n = 837 issues
19%
escalation rate
n = 1,017 runs
0%
rejected rate
n = 1,538 proposals
Pipeline

Stage funnel

proposed
1,538
promoted
855
56% of proposed
attempted
837
98% of promoted
passed gate
753
90% of attempted
published
742
99% of passed gate
merged
741
100% of published
By repository

Outcomes per repo

landed quarantined other
Orbit-Wars
80 · 86%
afk-agent-system
442 · 89%
afk-cockpit
106 · 94%
breakroom
5 · 40%
graphmark
14 · 93%
household-bms
48 · 96%
household-command-center
1 · 100%
housing-commute-analysis
15 · 93%
the-workshop
126 · 80%
Producers

Proposal quality

dropped
216
harvest
4
mis-sized
86
pending
375
rejected
1
shipped
855
superseded
1
Safety axis

Quarantine by category

278 total
other
85
no-op
35
review
24
capability
21
scope
19
integration-conflict
17
build-crash
16
deny-surface
10
setup-crash
10
test-conflict
10
circuit-breaker
7
timeout
5
coupling
4
idle-timeout
4
environmental
3
unrecoverable-signature
3
flaky-test
2
security
2
rate-limit
1
Retries & recovery

Runs per issue

1.22 avg runs/issue
12345
Retries & recovery

Quarantine → retry rescue

retry rescues 60% of first-run quarantines · 106% of those actually retried
74%
first-try pass rate
16%
final-state quarantine (issues)
27%
quarantine rate (runs)
Cost · API-equivalent
fleet telemetry · per attempt · Jun 7 – Aug 4, 2026

Spend by model tier

$2,567.68 total across the window
sonnet$1673.85 · avg $1.69/attempt · n=989 attempts
unknown tier$670.16 · avg $1.69/attempt · n=397 attempts
opus$223.67 · avg $2.46/attempt · n=91 attempts
⚠ 26% of attempt spend ($670.16 · 397 attempts) has no recorded model_tier — telemetry gap, not a model
Overhead · orchestrator + scout ops
$345.72
314 cost events · additive to the tier spend above · not a model tier
Claude Code transcripts, afk worktrees only · per API call · Jul 5 – Aug 4, 2026
$0.04
median / call
$0.08
p90 / call
13,093
calls logged
whole machine, all projects: $8,666.58 across 51,400 calls
Cost dial

Per-API-call cost distribution

9036
3253
525
173
82
18
6
<$.05.05–.10.10–.15.15–.20.20–.30.30–.50$.50+
Model mix

Opus share by day

Jul 5 range: 0%–70% Aug 4
Throughput

Slices per day

1,017 runs
06-0706-1306-1906-2707-0307-1407-2307-30
Context cost

Tokens by type, per day

970.2M tokens · 95.9% cache reads — the context is overwhelmingly cached
cache read cache write input output