Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install terminalWrote 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/madappgang/magus/terminal-interaction)<a href="https://agentmods.dev/skills/madappgang/magus/terminal-interaction"><img src="https://agentmods.dev/badge/skills/madappgang/magus/terminal-interaction/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/madappgang/magus/terminal-interaction"><img src="https://agentmods.dev/badge/skills/madappgang/magus/terminal-interaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.06070 |
| Opus 5 | $0.00018 | $0.03035 |
| Sonnet 5 | $0.00007 | $0.01214 |
| Haiku 4.5 | $0.00004 | $0.00607 |
Grade C, and why
terminal-interaction scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Unsubmitted input concatenates with your command.** tmux cannot see the shell's line buffer. If the user typed `rm -rf /data/` and never pressed Enter, the pane looks perfectly idle, and your command joins onto the e How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Interaction Skill
This skill teaches Claude how to use tmux-mcp for interactive terminal access: screen reading, keystroke injection, process monitoring, and TUI application navigation.
1. Tool selection
Every pane is addressed by a slot — an integer 1–64 — and by nothing else. You never hold a pane id; the server keeps the slot→pane map and places panes itself.
The slot convention, obeyed by every command in this plugin:
- Slot 1 is the visible helper beside the user, in the window they are looking at. Omit
slotand you get slot 1. - Private work takes
isolated: trueon slot 2 or higher — a pane nobody can see, on a private terminal server with no window. - Call
list-slotsbefore choosing a number when you may already hold slots (after compaction, or when resuming). Reusing a number reuses its pane.
| Scenario | Tool | Kind |
|---|---|---|
| One-shot command, nobody needs to watch | execute-command with isolated: true, no slot |
creating (ephemeral) |
| One-shot command beside the user | execute-command |
creating |
| Start a process, block until it is ready | start-and-watch |
creating |
| Type into a pane (commands, keys) | send-keys |
creating |
| Multi-step REPL session | run-in-repl |
creating |
| Show text to the user in a pane | write-to-display |
creating |
| Get a pane now, run something later | open-pane |
creating |
| Read the text of a slot | capture-pane |
reading |
| Render a slot as an image (colors, TUI layout) | screenshot-pane |
reading |
| Is the process alive / waiting for input | pane-state |
reading |
| Block until a slot changes, exits, or goes idle | watch-pane |
reading |
| Which slots do I hold | list-slots |
registry |
| Finish with a slot, or with all of them | close-pane |
registry |
| Transient message to the user (not a query) | notify |
none |
Decision rule: if the task involves waiting — for readiness, for output to change, for a REPL to respond — use start-and-watch, watch-pane or run-in-repl. For structural operations (get a pane, send a keystroke, read current state) use the rest.
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.
- yesterday Changed · -345 lines · -2 tokens per session fa44c617ad30
- 5d ago First seen · 679 lines · 38 tokens per session scan C 77e0f173c18a
terminal-interaction is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 6,070 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…