by lonely-lockley · Agent Tool · ★ 89
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Simplicity in Code, Power in Design
| Stars | 89 |
| Forks | 7 |
| Language | TypeScript |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 52.2156973113354/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-11 |
| Created | 2022-06-07 |
| Platforms | node, vscode |
| Est. Tokens | ~13k |
These tools work well together with archinsight for enhanced workflows:
Looking for a archinsight alternative? If you're comparing archinsight with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP o
google maps for vibecoders.
VSCode Extension with an MCP server that exposes semantic tools like Find Usages and Rename to LLMs
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Generate professional draw.io diagrams from natural language — a Claude Code skill
Claude Code Agent Monitoring & Observability on VSCode
Explore other popular agent tool tools:
archinsight is Simplicity in Code, Power in Design. It is categorized as a Agent Tool with 89 GitHub stars.
archinsight is primarily written in TypeScript. It covers topics such as agent-skills, architecture-as-code, architecture-diagrams.
You can find installation instructions and usage details in the archinsight GitHub repository at github.com/lonely-lockley/archinsight. The project has 89 stars and 7 forks, indicating an active community.
archinsight is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to archinsight on Agent Skills Hub include mcp-local-rag, claudemap, BifrostMCP. 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: