Your prompt says 'don't mention billing.' Your agent mentions billing. Pink Elephant finds the don'ts in prompts, skills, CLAUDE.md and AGENTS.md, rewrites them, and checks the rewrite with a blind reader. 92% fewer mentions.
Source
GitHub
Language
Python
Last activity
Oct 19, 2026
Stars3Measured · Oct 26, 2026
Momentum53.47 days · Measured · 0% relative change
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Source
GitHub
Language
Stata
Last activity
Oct 20, 2026
Stars4,780Measured · Oct 26, 2026
Momentum537 days · Measured · +1.94% relative change
Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.
Source
GitHub
Language
Python
Last activity
Oct 25, 2026
Stars4,916Measured · Oct 26, 2026
Momentum52.57 days · Measured · +1.84% relative change