shareAI-lab/learn-claude-code — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #783 · UNIT ID 1010681419

shareAI-lab/learn-claude-code

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00219

ENGAGEMENT1.04

FRESHNESS1.26

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

13% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

51.13

ACCEL

-0.47

RETENTION

13.8%

PEAK 2026-03-18 · FORK-RETENTION 56.7% · 9,204 STARS / WINDOW

Author Audience

AUDIENCE

23,327

FOLLOWERS

3,559

OWNER ★

81,047

Engagement Signals

FORKS

11,560

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 9,186 / 9,204 (DIVERSITY 1.00)

Why This Is A Finding

shareAI-lab/learn-claude-code собрал 9,204 звёзд за окно, тогда как у автора всего 3,559 подписчиков — эффективная аудитория ≈ 23,327. Это даёт surprise-индекс 0.00219 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 56.7% и 62 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 74% OF 2987 FINDINGS

#03originalankur/maptoposter[ PYTHON ]0.0234 #05HeartMuLa/heartlib[ PYTHON ]0.0222 #08sickn33/agentic-awesome-skills[ PYTHON ]0.0207 #14cft0808/edict[ PYTHON ]0.0183 #17aden-hive/hive[ PYTHON ]0.0175

METRICS IN CONTEXT

MEDIAN ACROSS ALL 2987 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 74%

VELOCITY51.132.84+48.29ABOVE 99%

RETENTION13.8%6.8%+7.0 PPABOVE 77%

FORKS11,5601,068+10,492ABOVE 94%

SURPRISE0.000.00+0.00ABOVE 68%