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/commands/madappgang/magus/run)<a href="https://agentmods.dev/commands/madappgang/magus/run"><img src="https://agentmods.dev/badge/commands/madappgang/magus/run/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/commands/madappgang/magus/run"><img src="https://agentmods.dev/badge/commands/madappgang/magus/run.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 | $0.00044 | $0.00760 |
| Opus 5.5 | $0.00018 | $0.00304 |
| Sonnet 5.5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
run scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
/terminal:run "curl -s https://api.example.com/health | jq" How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/terminal:run
Runs one command in an isolated pane the user never sees, returns the output and exit code, and leaves nothing open. This is the default terminal command for one-shot work.
Usage
/terminal:run {command}
Examples
/terminal:run npm test
/terminal:run go test ./... -v
/terminal:run "curl -s https://api.example.com/health | jq"
When to Use /terminal:run vs Bash
| Scenario | Use |
|---|---|
| Simple non-interactive command | Bash tool |
| Command with colored or formatted output | /terminal:run |
| Command with interactive prompts | /terminal:run |
| TUI-rendered output (progress bars, tables) | /terminal:run |
| Long-running continuous process | /terminal:watch instead |
| Multi-step REPL session | /terminal:repl instead |
Behavior
One-shot commands (the default path)
mcp__plugin_terminal_mux__execute-command({ command: "<user_command>", isolated: true })
→ { output, exitCode, timedOut }
With isolated: true and no slot, the pane is ephemeral: it opens, runs the command, and closes on its own. No slot number is held, so nothing needs cleaning up. Pass timeoutSeconds for commands that run longer than the default.
Commands that need streaming status
When the output should be watched as it arrives (a build with progress stages, a script that may hang), open an isolated slot and close it afterwards:
mcp__plugin_terminal_mux__start-and-watch({
slot: 2, isolated: true,
command: "<user_command>",
pattern: "\\$ $",
triggers: "exit,error",
timeout: 120
}) → { slot: 2, created: true, event, detail, elapsed, output, paneState }
mcp__plugin_terminal_mux__close-pane({ slot: 2 }) → [{ "slot": 2, "action": "killed" }]
event distinguishes success (pattern:…, exit) from error and timeout; output holds the transcript. Always close the slot, on every outcome.
Error Handling
- Command appears hung:
mcp__plugin_terminal_mux__pane-state({ slot: 2 })reportswaitingForInput. If it is waiting on a password prompt, stop and tell the user. event == "timeout": report the partial output, thenclose-pane({ slot: 2 }).- Stuck process:
mcp__plugin_terminal_mux__send-keys({ slot: 2, keys: "C-c", literal: false }), then close the slot.
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.
- 1mo ago Changed · -13 lines · +6 tokens per session 6ee2ff35a448
- 1mo ago First seen · 88 lines · 38 tokens per session scan A f5a3aa9cd115
run is a command published in the GitHub repository MadAppGang/magus (13 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 760 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
vios-sqa
VIOS SQA agent — build containers, deploy, run BDD tests, and validate web UI.
test
Generate integration tests for Alfresco extensions using Testcontainers (self-contained, no pre-running ACS required).
test-pr-docker
Test PR with Docker image build workflow.
test
Execute the test suite for Golden Armada agents.
implementar
Ejecutar tareas TDD fase por fase dentro de Docker hasta que todos los tests pasen.
Test Run
Execute the full test suite for Enonic XP agent skills against a Docker-based test environment. Covers script testing, template validation, functional skill testing, and reference accuracy checks.