opencode-claude-auth — security grade SAFE, quality 77/100

Security audit verdict: SAFE · quality 77/100

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 griffinmartin · Claude Skill · ★ 1.3k

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

🔒 Is opencode-claude-auth safe to install? View the security audit →

About opencode-claude-auth

opencode-claude-auth Self-contained Anthropic auth provider for OpenCode using your Claude Code credentials — no separate login or API key needed. How it works The plugin registers its own auth provider with a custom fetch handler that intercepts all Anthropic API requests. It reads OAuth tokens from the macOS Keychain (or on other platforms), caches them in memory with a 30-second TTL, and handles the full request lifecycle — no builtin Anthropic auth plugin required. It also syncs credentials to OpenCode's as a fallback (on Windows, it writes to both and to cover all installation methods). If a token is near expiry, it runs the Claude CLI to trigger a refresh. Background re-sync runs every 5 minutes. Prerequisites Claude Code installed and authenticated (r

aianthropicauthenticationclaudeclaude-codehomebrewnodejsoauthopencodeopencode-plugin

Quick Facts

Stars1,281
Forks182
LanguageTypeScript
CategoryClaude Skill
LicenseMIT
Quality Score76.8642000009446/100
Open Issues21
Last Updated2026-09-22
Created2026-03-19
Platformsclaude-code, node
Est. Tokens~16k

Compatible Skills

These tools work well together with opencode-claude-auth for enhanced workflows:

opencode-claude-auth alternative? Top 6 similar tools

Looking for a opencode-claude-auth alternative? If you're comparing opencode-claude-auth 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.

  • zcf by UfoMiao · ⭐ 6.1k

    Zero-Config Code Flow for Claude code & Codex

  • ax by ax-llm · ⭐ 3.0k

    The pretty much "official" DSPy framework for Typescript

  • ccs by kaitranntt · ⭐ 2.9k

    Switch between Claude accounts, Gemini, Copilot, OpenRouter (300+ models) via CLIProxyAPI OAuth proxy. Visual

  • agentsys by agent-sh · ⭐ 991

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

  • opencode-with-claude by ianjwhite99 · ⭐ 593

    OpenCode plugin to use your Claude Max/Pro subscription with OpenCode via Meridian

  • openpencil by ZSeven-W · ⭐ 6.1k

    The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. De

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is opencode-claude-auth?

opencode-claude-auth is OpenCode plugin that uses your existing Claude Code credentials — no separate login needed.. It is categorized as a Claude Skill with 1.3k GitHub stars.

What programming language is opencode-claude-auth written in?

opencode-claude-auth is primarily written in TypeScript. It covers topics such as ai, anthropic, authentication.

How do I install or use opencode-claude-auth?

You can find installation instructions and usage details in the opencode-claude-auth GitHub repository at github.com/griffinmartin/opencode-claude-auth. The project has 1.3k stars and 182 forks, indicating an active community.

What license does opencode-claude-auth use?

opencode-claude-auth is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to opencode-claude-auth?

The top alternatives to opencode-claude-auth on Agent Skills Hub include zcf, ax, ccs. 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