by zanetworker · LLM Plugin · ★ 11
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 | 11 |
| Forks | 0 |
| Language | Go |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 69/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-21 |
| Created | 2026-06-23 |
| Platforms | cli, go |
| Est. Tokens | ~18k |
AI writes code faster than you can review it. HighStakes reads your codebase, scores every file by blast radius, and tells you where human review matters and where AI can handle the rest.
Looking for a highstakes alternative? If you're comparing highstakes with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
htop for your AI costs — real-time terminal monitoring of LLM token usage and spending across providers and co
✋ Interactive CLI tool for selecting and bundling code into a single, LLM-ready output file
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph,
Process manager for AI agents (and humans)
A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama
CLI tool that generates commit messages from git changes, reviews code for quality issues, and provides debugg
Explore other popular llm plugin 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: