Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/MadAppGang/magusWrote 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/plugins/madappgang/magus/terminal)<a href="https://agentmods.dev/plugins/madappgang/magus/terminal"><img src="https://agentmods.dev/badge/plugins/madappgang/magus/terminal.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
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 2d 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.
What it actually says
{
"name": "terminal",
"version": "4.2.0",
"description": "Intent-level terminal control over tmux. Runs interactive commands, dev servers, test watchers, REPLs and TUI apps in a helper pane that the server places and owns, so an agent never targets the user's own session.",
"author": {
"name": "Jack Rudenko",
"email": "[email protected]",
"company": "MadAppGang"
},
"license": "MIT",
"keywords": [
"terminal",
"pty",
"tui",
"interactive",
"tmux",
"headless",
"run",
"watch",
"repl",
"dev-server",
"test-watcher"
],
"category": "development",
"skills": [
"./skills/terminal-interaction",
"./skills/tui-navigation-patterns",
"./skills/framework-signals",
"./skills/tdd-workflow",
"./skills/workspace-setup"
],
"setup": {
"go": [
"github.com/MadAppGang/[email protected]"
],
"required": [
"tmux"
]
},
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 5 skills, 7 commands, 1 agent travel with it, and installing the plugin installs all of them — 436 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill tui-navigation-patterns A 55 tokens
- Skill tdd-workflow A 51 tokens
- Skill workspace-setup A 43 tokens
- Skill framework-signals A 52 tokens
- Skill terminal-interaction C 38 tokens
- Command send A 14 tokens
- Command session A 19 tokens
- Command observe A 28 tokens
- Command repl A 44 tokens
- Command run A 38 tokens
- Command watch A 38 tokens
- Command snapshot A 16 tokens
- Agent tui-navigator A 0 tokens
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.
- 2d ago First seen · 42 lines scan A 463948d07d74
terminal is a plugin published in the GitHub repository MadAppGang/magus (9 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-04.
Other plugins, from other repositories
set-up-ci
Set up GitHub Actions CI with test, lint, format, and vulnerability check jobs, plus matching Makefile targets.
shipshitdev-testing
Testing, QA, and CI/CD automation skills.
preflight
Multi-agent CI/CD pipeline ensuring Python packages pass cross-platform, multi-version, and quality gates before shipping to GitHub or PyPI.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.