cc-agent-sdk: 基于 claude code sdk 的 agent api,兼容Skills + Sub Agents

by Auto-200 · Agent Tool · ★ 53

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

How to install cc-agent-sdk

docker compose up -d cc-agent-sdk-dev

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 62/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars53
Forks4
LanguageTypeScript
CategoryAgent Tool
Quality Score62/100
Last Updated2026-05-01
Created2025-12-18
Platformsclaude-code, node
Est. Tokens~6k

About cc-agent-sdk

cc-agent-sdk 本仓库是一个轻量的本地 Claude Agent SDK 代理服务(TypeScript + Bun),提供 HTTP POST + SSE 的流式接口,方便其他 Worker/DO 通过统一入口调用 Claude Agent SDK(或 Anthropic 兼容 API)。 官方 SDK 参考文档已收纳到 目录(未改动原文)。 快速开始 默认监听:(可用环境变量 调整) 可选鉴权:设置 后,所有请求需带头: Docker(GitHub Actions 自动构建) 本仓库包含一个 GitHub Actions workflow:每次 push 到 或打 tag(如 )会自动构建并推送镜像到 GHCR: 镜像地址: Tags: :仅默认分支(通常是 ) :分支 tag :发布 tag(如 ) :提交哈希 拉取示例: Docker 本地运行(Compose)...

Compatible Skills

These tools work well together with cc-agent-sdk for enhanced workflows:

  • sub-agents-mcp — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (54%)
  • sub-agents.directory — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (54%)
  • n8n-nodes-claudecode — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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:

View on GitHub → Browse Agent Tool tools