Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.
Borrowing it
Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/skills/tmux-terminal/SKILL.mdgit clone --depth 1 https://github.com/mikeyobrien/ralph-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mikeyobrien/ralph-orchestrator/tmux-terminal)<a href="https://agentmods.dev/skills/mikeyobrien/ralph-orchestrator/tmux-terminal"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/tmux-terminal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mikeyobrien/ralph-orchestrator/tmux-terminal"><img src="https://agentmods.dev/badge/skills/mikeyobrien/ralph-orchestrator/tmux-terminal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00677 |
| Opus 5 | $0.00012 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
tmux-terminal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux-terminal
Overview
Use tmux to drive interactive terminal sessions, including TUI workflows like ralph-tui. tmux lets you send keystrokes, capture screen output, and keep processes running between steps.
When to Use
- Testing
ralph-tuior any interactive CLI prompts - Managing long-running processes (web server, loops, watch mode)
- Capturing live terminal output for QA reports
- Interacting with applications that redraw the screen
Prerequisites
tmuxinstalled (pre-installed on macOS)
Verify:
tmux -V
Core Commands
Create a detached session:
tmux new-session -d -s <name>
Send commands (append Enter to execute):
tmux send-keys -t <name> "<command>" Enter
Capture screen output:
tmux capture-pane -t <name> -p
Kill session when done:
tmux kill-session -t <name>
Special Keys
Use send-keys with key names:
EnterC-c(Ctrl-C)C-d(Ctrl-D)TabEscapeUp,Down,Left,Right
Examples:
tmux send-keys -t <name> Up
tmux send-keys -t <name> C-c
TUI Interaction Patterns
Start ralph-tui
tmux new-session -d -s ralph-tui
tmux send-keys -t ralph-tui "cargo run -p ralph-tui" Enter
Navigate in TUI
tmux send-keys -t ralph-tui Down
tmux send-keys -t ralph-tui Enter
Capture and parse the screen
tmux capture-pane -t ralph-tui -p -S -200
Use -S -200 to capture the last 200 lines when the screen is noisy.
Long-Running Process Management
- Start servers or loops in a tmux session to keep them alive.
- Use
capture-paneto confirm health (look for "listening" or "ready" text). - Stop cleanly with
C-cthenkill-session.
Example:
tmux new-session -d -s ralph-web
tmux send-keys -t ralph-web "cargo run -p ralph-cli -- web" Enter
tmux capture-pane -t ralph-web -p | rg -n "listening|ready"
tmux send-keys -t ralph-web C-c
tmux kill-session -t ralph-web
Notes
- Keep session names short and unique.
- Always clean up sessions to avoid leaking background processes.
- If output looks empty, wait briefly and capture again.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 110 lines · 23 tokens per session scan A 8b102030d539
tmux-terminal is a skill published in the GitHub repository mikeyobrien/ralph-orchestrator (3,132 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 677 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
teams-notifications
Microsoft Teams MCP integration for agent-to-human notifications and bi-directional communication. Use when agents need to post progress updates, request approvals, or read user responses via Teams channels and chats.
self-improvement
Appends new entries to LESSONS-LEARNED.md via opencastle lesson CLI; searches past lessons for matching errors; proposes skill updates when retry patterns exceed thresholds. Use when consulting or updating LESSONS-LEARNED.md, after task failures, when capturing retrospective insights, or when a retry succeeds.
slack-notifications
Slack MCP integration for agent-to-human notifications and bi-directional communication. Use when agents need to post progress updates, request approvals, or read user responses via Slack channels and threads.
help
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available.
resume-handoff
Resume work from handoff document with context analysis and validation.
repoprompt
Use RepoPrompt CLI for token-efficient codebase exploration.