compass — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 crabbuild · Claude Skill · ★ 161

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is compass safe to install? View the security audit →

About compass

Compass A fast, local-first knowledge graph for understanding codebases. Compass turns source code and project artifacts into a graph you can search, query, visualize, compare across Git history, and share with development tools. Get started · Read the documentation · Explore the roadmap · View releases Use Compass inside your editor with the first-party Compass Codegraph extension for VS Code. See the VS Code extension guide for current graphs, cursor-rooted call graphs, architecture flow, queries, and exact Git evolution. What Compass gives you | Aut

aiai-agentsai-codingai-toolsclaudeclaude-codeclaude-skillscode-qualitycodegraphcodex

Quick Facts

Stars161
Forks8
LanguageRust
CategoryClaude Skill
Quality Score63.79263396082/100
Open Issues6
Last Updated2026-09-21
Created2026-07-22
Platformsclaude-code, codex, rust
Est. Tokens~25k

Compatible Skills

These tools work well together with compass for enhanced workflows:

  • graphmind — semantic(0.41)+complementary+rare_topics+same_lang+similar_pop+shared_platform (69%)
  • code-graph-mcp — semantic(0.38)+complementary+same_lang+similar_pop+shared_platform (63%)
  • arbor — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • planr — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

compass alternative? Top 6 similar tools

Looking for a compass alternative? If you're comparing compass 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.

  • vsync by nicepkg · ⭐ 55

    Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools

  • vnx-orchestration by Vinix24 · ⭐ 61

    Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality ga

  • tree-sitter-analyzer by aimasteracc · ⭐ 50

    Cross-language-safe code-intelligence MCP for AI agents: 13 languages, family-gated call graph, blast radius,

  • octocode by Muvon · ⭐ 477

    Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o

  • agnix by agent-sh · ⭐ 422

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • deepcontext-mcp by Wildcard-Official · ⭐ 278

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is compass?

compass is Native, local-first knowledge graph engine for code and project artifacts—inspired by Graphify, built in Rust, and evolving beyond it.. It is categorized as a Claude Skill with 161 GitHub stars.

What programming language is compass written in?

compass is primarily written in Rust. It covers topics such as ai, ai-agents, ai-coding.

How do I install or use compass?

You can find installation instructions and usage details in the compass GitHub repository at github.com/crabbuild/compass. The project has 161 stars and 8 forks, indicating an active community.

What are the best alternatives to compass?

The top alternatives to compass on Agent Skills Hub include vsync, vnx-orchestration, tree-sitter-analyzer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools