Piebald-AI/claude-code-system-prompts — GitHub trend

FINDING #1374 · UNIT ID 1099328966

Piebald-AI/claude-code-system-prompts

All parts of Claude Code's system prompt, 27 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

[ JAVASCRIPT ][ ORG ][ VERIFIED ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00156

ENGAGEMENT0.51

FRESHNESS1.06

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

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

13% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

8.32

ACCEL

-0.11

RETENTION

4.8%

PEAK 2026-04-01 · FORK-RETENTION 23.5% · 1,498 STARS / WINDOW

Author Audience

AUDIENCE

5,290

FOLLOWERS

445

OWNER ★

15,965

Engagement Signals

FORKS

2,008

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 1,495 / 1,498 (DIVERSITY 1.00)

Why This Is A Finding

Piebald-AI/claude-code-system-prompts собрал 1,498 звёзд за окно, тогда как у автора всего 445 подписчиков — эффективная аудитория ≈ 5,290. Это даёт surprise-индекс 0.00156 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 23.5% и 4 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 54% OF 2987 FINDINGS

#12affaan-m/ECC[ JAVASCRIPT ]0.0192 #18thedotmack/claude-mem[ JAVASCRIPT ]0.017 #291186258278/OpenClawChineseTranslation[ JAVASCRIPT ]0.0148 #45hzm0321/real-time-fund[ JAVASCRIPT ]0.0132 #59santifer/career-ops[ JAVASCRIPT ]0.0124

METRICS IN CONTEXT

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

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 54%

VELOCITY8.322.84+5.48ABOVE 85%

RETENTION4.8%6.8%-2.1 PPABOVE 37%

FORKS2,0081,068+940ABOVE 65%

SURPRISE0.000.00+0.00ABOVE 63%