by nirholas · Claude Skill · ★ 6.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 6,238 |
| Forks | 17 |
| Language | TypeScript |
| Category | Claude Skill |
| Quality Score | 46/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-10 |
| Created | 2026-03-31 |
| Platforms | claude-code, node |
| Est. Tokens | ~868k |
Fresh Start This is the repository formerly known as , the most widely forked mirror of the Claude Code source leak of 31 March 2026. It is the same repository object, so still redirects here. It contains no Anthropic source code, and it will not. The contents were removed after Anthropic's DMCA notice. That notice has not been retracted.
These tools work well together with fresh-start for enhanced workflows:
Looking for a fresh-start alternative? If you're comparing fresh-start with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you co
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particular
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng
Ultimate collection of Claude Code tips, tricks, hacks, and workflows that you can use to master Claude Code i
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, sessio
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: