No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by PaulRBerg · Claude Skill · ★ 82
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dot-claude safe to install? View the security audit →
Claude Code config PRB's directory. Quick Start See Installation for full setup and Configuration for customization. Installation Prerequisites Node.js: Husky/lint-staged automation () Just: command runner for build scripts () Python 3.13+ and uv: Python package/project manager Setup Verify Configuration Settings All JSONC files in merge into on commit via Husky + lint-staged. Edit only (never directly). Merging happens on commit, or run manually
| Stars | 82 |
| Forks | 13 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 74.06095021782/100 |
| Open Issues | 10 |
| Last Updated | 2026-10-13 |
| Created | 2025-08-31 |
| Platforms | claude-code, python |
| Est. Tokens | ~14k |
Looking for a dot-claude alternative? If you're comparing dot-claude 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.
MCP implementation of Claude Code capabilities and more
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
📜 An MCP server for conversation history search and retrieval in Claude Code
Giving Claude ability to run code with E2B via MCP (Model Context Protocol)
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
Explore other popular claude skill tools:
dot-claude is PRB's Claude Code config. It is categorized as a Claude Skill with 82 GitHub stars.
dot-claude is primarily written in Python. It covers topics such as claude, claude-code.
You can find installation instructions and usage details in the dot-claude GitHub repository at github.com/PaulRBerg/dot-claude. The project has 82 stars and 13 forks, indicating an active community.
dot-claude is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to dot-claude on Agent Skills Hub include mcp-claude-code, deepcontext-mcp, claudex. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: