codeArbiter — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

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 arbiterForge · Claude Skill · ★ 145

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

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

About codeArbiter

Shared enforcement and project-context parity across Claude Code, Codex CLI, and Pi. One repository-owned governance layer for tests, reviews, security checks, decisions, and durable project context. You decide. codeArbiter enforces. Start learning   ·   Install   ·   Browse the reference Install it globally. It stays dormant until a repository explicitly opts in. Agentic coding, with a record codeArbiter is for teams and power users who let coding agent

aiai-agentsai-codingai-governanceai-safetyai-toolschatgptclaudeclaude-codeclaude-code-plugin

Quick Facts

Stars145
Forks7
LanguagePython
CategoryClaude Skill
LicenseAGPL-3.0
Quality Score61.7260150279927/100
Open Issues33
Last Updated2026-09-20
Created2026-05-08
Platformsclaude-code, cli, codex, python
Est. Tokens~19k

Compatible Skills

These tools work well together with codeArbiter for enhanced workflows:

  • agent-skills — semantic(0.47)+complementary+same_lang+similar_pop+shared_platform (66%)
  • skills — semantic(0.44)+complementary+same_lang+similar_pop+shared_platform (65%)
  • codex-reset-credits-skill — semantic(0.39)+complementary+same_lang+similar_pop+shared_platform (64%)

codeArbiter alternative? Top 6 similar tools

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

  • smart-ralph by tzachbon · ⭐ 544

    Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • maestro-orchestrate by josstei · ⭐ 464

    Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, paralle

  • forge-orchestrator by nxtg-ai · ⭐ 135

    Forge Orchestrator: Multi-AI task orchestration. File locking, knowledge capture, drift detection. Rust.

  • forgecat-agent-profiles by nota-america · ⭐ 77

    Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and

  • claude-elixir-phoenix by oliver-kriska · ⭐ 553

    Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is codeArbiter?

codeArbiter is When you can't trust yourself with your code base, trust Arbiter.. It is categorized as a Claude Skill with 145 GitHub stars.

What programming language is codeArbiter written in?

codeArbiter is primarily written in Python. It covers topics such as ai, ai-agents, ai-coding.

How do I install or use codeArbiter?

You can find installation instructions and usage details in the codeArbiter GitHub repository at github.com/arbiterForge/codeArbiter. The project has 145 stars and 7 forks, indicating an active community.

What license does codeArbiter use?

codeArbiter is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to codeArbiter?

The top alternatives to codeArbiter on Agent Skills Hub include smart-ralph, hcom, maestro-orchestrate. 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