FINDING #2355 · UNIT ID 1122859216
the-open-engine/zeroshot
Your autonomous engineering team in a CLI. The agent loop produces senior-level code that you can actually trust in prod because of non-negotiable feedback from independent reviewers. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI with trivial setup.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
40% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
3.73
ACCEL
-0.02
RETENTION
19.8%
PEAK 2026-03-13 · FORK-RETENTION 0.0% · 672 STARS / WINDOW
Author Audience
AUDIENCE
375
FOLLOWERS
20
OWNER ★
1,675
Engagement Signals
FORKS
142
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 672 / 672 (DIVERSITY 1.00)
Why This Is A Finding
the-open-engine/zeroshot собрал 672 звёзд за окно, тогда как у автора всего 20 подписчиков — эффективная аудитория ≈ 375. Это даёт surprise-индекс 0.009 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 74% OF 8934 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 8934 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00+0.00ABOVE 74%
VELOCITY3.733.18+0.56ABOVE 56%
RETENTION19.8%9.9%+9.9 PPABOVE 75%
FORKS142107+35ABOVE 59%
SURPRISE0.010.01+0.00ABOVE 51%