Ghost Engineering Benchmarks

Ghost · GitHub · Updated July 28, 2026

Ghost delivery benchmarks are based on 546 merged pull requests in the last 30 days (3,158 all-time), with 1.9 hours median cycle time, 0.2 hours median review time, and 40 active contributors. AI-related signals appear on 6.0% of recent work. PR volume is down -7% compared to the prior period.

Median Cycle Time
1.9h
PR open to merge
Median Review Time
0.2h
first review to approval
AI-Related Signals
6.0%
directional signal across recent PRs
Best Signal Fast Delivery
1.9h
Median cycle time of 1.9h

Repo vs Ghost Average

-3.2pp
AI Signals
-0.5h
Cycle Time
+0.0h
Review Time

Delivery Trend and AI Signals

PR Backlog (Humans)

Excludes AI agents and automation accounts.

PR Backlog (AI Agents)

AI coding agents only.

Top AI Coding Agents

Most active AI coding agents in the last 90 days.

AI Signals vs Cycle Time

Correlation

moderate positive
r = 0.40 (14 weeks)

Cycle Time by AI-Related Signals

35.1h
with signals
24.6h
baseline
42.9%
difference

PR Breakdown

163 with signals / 575 total PRs

Top AI Tools

coderabbit 116
claude 22
chatgpt 11
claude_code 9
copilot 3

PR Type Breakdown

unknown 202
refactor 98
bugfix 85
chore 72
feature 45
ci 26

Methodology

Metrics are computed from merged pull request data synced daily from GitHub. AI-related metrics are directional signals inferred from pull request activity patterns and heuristics. Summary metrics use a 30-day rolling window; trends use a 90-day window. Last updated 27 minutes ago.

Updated daily from public GitHub pull requests.

See Your Team's Benchmarks

Get this analytics stack for your team

Connect GitHub and see cycle time, review bottlenecks, PR flow, and trend changes in minutes.

Connect Repos