by OMARVII · MCP Server · ★ 122
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
| Stars | 122 |
| Forks | 6 |
| Language | Shell |
| Category | MCP Server |
| License | MIT |
| Quality Score | 77/100 |
| Last Updated | 2026-05-17 |
| Created | 2026-04-07 |
| Platforms | claude-code, cli, mcp |
| Est. Tokens | ~31k |
Claude Alloy A mixture stronger than its parts. Quick Start • Agents • Install • Dev Guide • Contributing ig activates IGNITE mode — steel verbalizes intent, fires specialists in parallel, and the HUD tracks context / cost / quota live. Claude Code with a team. Fourteen specialist agents. Model-tiered (Opus/Sonnet/Haiku) so you stop overpaying for searches. Zero runtime.
These tools work well together with claude-alloy for enhanced workflows:
Looking for a claude-alloy alternative? If you're comparing claude-alloy with other mcp server 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
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
The Complete AI Development Toolkit for Claude Code. 115 skills, 36 agents, 161 hooks. Install `ork` for stabl
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Cl
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs
Explore other popular mcp server 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: