claude-relay
Relay operator for Claude Code via tmux across multiple projects. Use when the user wants to start/continue a Claude Code terminal session, send prompts, read output, or manage background Claude sessions by project name/path.
Best use case
claude-relay is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Relay operator for Claude Code via tmux across multiple projects. Use when the user wants to start/continue a Claude Code terminal session, send prompts, read output, or manage background Claude sessions by project name/path.
Teams using claude-relay should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/claude-relay/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How claude-relay Compares
| Feature / Agent | claude-relay | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Relay operator for Claude Code via tmux across multiple projects. Use when the user wants to start/continue a Claude Code terminal session, send prompts, read output, or manage background Claude sessions by project name/path.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Claude Relay Operate Claude Code as a persistent terminal copilot through tmux. ## Script All actions go through `scripts/relay.sh`. Run with no args for usage help. ```bash scripts/relay.sh <action> [project] [args...] ``` **Actions**: `start`, `send`, `tail`, `stop`, `status`, `session` ## Workflow 1. Start session: `scripts/relay.sh start <project>` 2. Send instruction: `scripts/relay.sh send <project> "<text>"` 3. Read output: `scripts/relay.sh tail <project> [lines]` 4. Repeat send/tail as needed. 5. Stop when done: `scripts/relay.sh stop <project>` ## Project resolution The script resolves `<project>` in order: 1. Absolute path (if directory exists) 2. Alias from `projects.map` (`name=/abs/path`) 3. `$CLAUDE_RELAY_ROOT/<name>` exact match 4. Find under `$CLAUDE_RELAY_ROOT` (maxdepth=2) by folder name 5. If omitted, re-use last project Multiple matches → script exits with candidates; ask user to clarify. ## Session naming Deterministic: `cc_<basename_sanitized>`. One project = one tmux session. ## Error handling - **tmux not installed**: script exits with code 2 and "missing dependency" message. - **Claude binary not found**: same exit code 2. Verify `CLAUDE_BIN` env or default path. - **Session not running** (send/tail on stopped session): exits code 6. Start first. - **Project not found**: exits code 4. Check `projects.map` or project path. - **Claude process hung**: `tail` still works — check output. If stuck, `stop` and `start` fresh. ## Environment variables | Variable | Default | Description | |----------|---------|-------------| | `CLAUDE_RELAY_ROOT` | `$HOME/projects` | Root directory for project discovery | | `CLAUDE_RELAY_MAP` | `<skill-dir>/projects.map` | Path to project alias map file | | `CLAUDE_BIN` | `claude` (from PATH) | Path to Claude Code CLI binary | | `RELAY_WAIT` | `6` | Seconds to wait after send before tailing output | ## Setup 1. Install this skill 2. Create a `projects.map` file in the skill directory (see `projects.map.example`) 3. Ensure `tmux` and `claude` are installed and in your PATH ## Notes - Transport-focused skill (relay/orchestration), not deep code reasoning.
Related Skills
afrexai-claude-code-production
Complete Claude Code productivity system — project setup, prompting patterns, sub-agent orchestration, context management, debugging, refactoring, TDD, and shipping 10X faster. Zero scripts needed.
ask-claude
Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).
captcha-relay
Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captures the page with a grid overlay, sends it to the human, and injects clicks based on their reply. Token relay mode detects CAPTCHA type + sitekey, serves the real widget on a relay page for native solving, and injects the token via CDP.
claude-audit
Full project audit — launches 5 parallel AI agents (security, bugs, dead code, architecture, performance) to scan your codebase read-only, then compiles a unified report with health grade (A+ to F) and offers surgical fixes. Language-agnostic. Zero config.
Claude Skills 开发框架架构指导手册
## 1. 项目概述 (Overview)
claude-code-usage
Check Claude Code OAuth usage limits (session & weekly quotas). Use when user asks about Claude Code usage, remaining limits, rate limits, or how much Claude usage they have left. Includes automated session refresh reminders and reset detection monitoring.
ClaudeHemat
# Introduction
claude-code-cli
Delegate coding tasks to Claude Code CLI via background process. Use when: building features, reviewing PRs, refactoring codebases, or iterative coding that needs file exploration. Supports interactive PTY mode for confirmations/permissions and headless pipe mode for automation. NOT for: simple one-liner fixes (just edit), reading code (use read tool), or any work in ~/.openclaw/ workspace.
Claude Code CLI for OpenClaw
Install, authenticate, and use Claude Code CLI as a native coding tool for any OpenClaw agent system.
claude-usage
Check Claude Code / Claude Max usage limits. Run when user asks about usage, limits, quota, or how much Claude capacity is left.
claude-notifications
Set up native macOS notifications for Claude Code on local and devpod/remote environments. Use when the user asks to 'setup notifications', 'configure devpod notifications', 'get notified when Claude needs attention', 'setup claude alerts', or 'install notification hooks'. Handles local terminal-notifier, SSH reverse tunnel for devpods, launchd listener, tmux passthrough, and Claude Code hook configuration.
claude-code-statusline
Install and configure a custom Claude Code status line showing real-time token usage, context window percentage, git branch, and color-coded warnings. Use when the user asks to "install statusline", "setup statusline", "configure statusline", "setup status line", "install status bar", "show token usage", "context window display", "statusline colors", "statusline thresholds", or wants to customize their Claude Code status bar display.