by JuliusBrussee · Claude Skill · ★ 675
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npm install -g cavememTaken from the project's README on GitHub. Check the security audit before running it.
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 | 675 |
| Forks | 58 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 74/100 |
| Open Issues | 12 |
| Last Updated | 2026-08-14 |
| Created | 2026-04-18 |
| Platforms | claude-code, node |
| Est. Tokens | ~15k |
cavemem why agent forget when agent can remember Install • How it works • CLI • MCP • Settings 🪨 Caveman Ecosystem · caveman talk less · cavemem remember more (you are here) · cavekit build better Cross-agent persistent memory for coding assistants.
These tools work well together with cavemem for enhanced workflows:
Looking for a cavemem alternative? If you're comparing cavemem 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.
One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosyst
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Long-term memory layer for OpenClaw & MoltBook agents that learns and recalls your project context automatical
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It
📜 An MCP server for conversation history search and retrieval in Claude Code
Your friendly, blazing-fast, self-hostable AI gateway
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: