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 V-Songbird · Claude Skill · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hush safe to install? View the security audit →
hush Claude narrates every step and dumps every log line into your chat. hush gives you one short answer at the end instead. The same eight jobs, Claude Opus 5, 32 sessions each way. Install · What is this? ·
| Stars | 50 |
| Forks | 4 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 64.5355202463847/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-15 |
| Created | 2026-07-07 |
| Platforms | claude-code, node |
| Est. Tokens | ~15k |
Looking for a hush alternative? If you're comparing hush 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.
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Air traffic control discipline for agent output. Written for a reader with ADHD.
Finish What You Start — Context engineering for Claude Code. Sessions last 20+ exchanges instead of cr
iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group variou
📜 An MCP server for conversation history search and retrieval in Claude Code
Explore other popular claude skill tools:
hush is Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.. It is categorized as a Claude Skill with 50 GitHub stars.
hush is primarily written in JavaScript. It covers topics such as adhd, agent-skills, ai.
You can find installation instructions and usage details in the hush GitHub repository at github.com/V-Songbird/hush. The project has 50 stars and 4 forks, indicating an active community.
hush is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to hush on Agent Skills Hub include claude-emporium, claudepro-directory, attention-control. 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: