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 kbwo · Claude Skill · ★ 1.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ccmanager safe to install? View the security audit →
CCManager - AI Code Agent Session Manager CCManager is a CLI application for managing multiple AI coding assistant sessions (Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, Kimi CLI) across Git worktrees and projects. https://github.com/user-attachments/assets/15914a88-e288-4ac9-94d5-8127f2e19dbf Features Run multiple AI assistant sessions in parallel across different Git worktrees Multi-project support: Manage multiple git repositories from a single interface Support for multiple AI coding assistants (Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, Kimi CLI) Switch between sessions seamlessly Visual status indicators for session states (busy, waiting, idle) Create, merge, and delete worktrees from within the app Copy Claude Code session data between worktrees to maintain conversation context Configurable keyboard shortcuts Command presets with automatic fallback support Configurable state detection strategies for different CLI tools Status change hooks for automation and notifications Devcontainer integration Auto Approval (experimental): Automatically approve safe prompts using AI verification Why CCManager...
| Stars | 1,240 |
| Forks | 92 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 76.3314580392541/100 |
| Open Issues | 9 |
| Last Updated | 2026-09-13 |
| Created | 2025-06-07 |
| Platforms | claude-code, cli, codex, gemini, node |
| Est. Tokens | ~17k |
These tools work well together with ccmanager for enhanced workflows:
Looking for a ccmanager alternative? If you're comparing ccmanager 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.
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports M
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode,
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of toke
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici
Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent S
Explore other popular claude skill tools:
ccmanager is Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI / OpenCode / Kimi CLI. It is categorized as a Claude Skill with 1.2k GitHub stars.
ccmanager is primarily written in TypeScript. It covers topics such as claude, claude-code, cli.
You can find installation instructions and usage details in the ccmanager GitHub repository at github.com/kbwo/ccmanager. The project has 1.2k stars and 92 forks, indicating an active community.
ccmanager is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to ccmanager on Agent Skills Hub include agent-of-empires, claude_codex_bridge, tokscale. 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: