by henchmarketing-rgb · Claude Skill · ★ 69
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 | 69 |
| Forks | 4 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 71/100 |
| Last Updated | 2026-04-24 |
| Created | 2026-04-23 |
| Platforms | claude-code, cli |
| Est. Tokens | ~11k |
headroom You're deep in a session. Claude starts dropping earlier context. Compaction fires mid-turn and takes work in progress with it. You had no warning. Claude Code gives you nothing on context usage. headroom fixes that. A live bar in your statusline, updated after every tool call. Now you can see the window filling up.
Looking for a headroom alternative? If you're comparing headroom 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.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Know your quota before you hit the wall. The only pace-aware statusline for Claude Code.
A curated collection of awesome plugins for Claude Code by awesomejun
Supercharge your Claude Code CLI experience with a powerful statusline that displays key session metrics (Git
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Config-driven CLI tool that compresses command output before it reaches an LLM context
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: