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 jfrog · Codex Skill · ★ 502
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is boost safe to install? View the security audit →
Make your agents smarter and faster Smart token savings for coding agents, shell commands, and CI. <img
| Stars | 502 |
| Forks | 21 |
| Language | Shell |
| Category | Codex Skill |
| Quality Score | 62.7781040284019/100 |
| Open Issues | 10 |
| Last Updated | 2026-09-22 |
| Created | 2026-03-02 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~12k |
These tools work well together with boost for enhanced workflows:
Looking for a boost alternative? If you're comparing boost with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Co
CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, G
The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic S
Explore other popular codex skill tools:
boost is Save tokens. Maximize context, Safely. It is categorized as a Codex Skill with 502 GitHub stars.
boost is primarily written in Shell. It covers topics such as acceleration, ai, ai-agents.
You can find installation instructions and usage details in the boost GitHub repository at github.com/jfrog/boost. The project has 502 stars and 21 forks, indicating an active community.
The top alternatives to boost on Agent Skills Hub include OpenContext, codesight, snip. 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: