A read-only tool for inspecting running tmux terminal sessions and panes. It can list active sessions, show current output, or wait until a pane changes.

Use it to inspect terminal output, check whether a development server or test watcher is progressing, and monitor a pane for changes.

It lets an agent check servers, test watchers, and other running processes without sending keystrokes or changing their state.

observe — Command for Claude Code by MadAppGang/magus

Install

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.

Clone the repo

git clone --depth 1 https://github.com/MadAppGang/magus

Made for: Claude Code.

Or install terminal, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 1 agent.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/madappgang/magus/observe/github.svg)](https://agentmods.dev/commands/madappgang/magus/observe)

Your own site

<a href="https://agentmods.dev/commands/madappgang/magus/observe"><img src="https://agentmods.dev/badge/commands/madappgang/magus/observe/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/madappgang/magus/observe"><img src="https://agentmods.dev/badge/commands/madappgang/magus/observe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 680 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00047	$0.00680
Opus 5.5	$0.00019	$0.00272
Sonnet 5.5	$0.00009	$0.00136
Haiku 4.5	$0.00005	$0.00068

Measured 1mo ago against content hash a5cf7a1fa06f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

observe 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 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.

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.

plugins/terminal/commands/observe.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/terminal:observe

Read-only observation of the slots this session holds. Lists what is open, captures a slot's content, and checks on processes without sending anything.

Usage

/terminal:observe
/terminal:observe {slot}
/terminal:observe {slot} --watch

What It Does

No arguments: mcp__plugin_terminal_mux__list-slots shows every slot, then capture-pane reads slot 1.
With a slot number: captures that slot's last 50 lines.
With --watch: blocks in watch-pane until the process exits, prints an error, or goes idle for 30 seconds.

This command never sends keystrokes or closes a slot. It can only read slots this session opened; a slot that was never opened is an error, not a new pane.

Examples

See what is running:

/terminal:observe
→ [{ "slot": 1, "isolated": false, "origin": "created", "foregroundCmd": "node", "isAlive": true }]

Check on a dev server started with /terminal:watch:

/terminal:observe 1

Wait for a test watcher in an isolated slot to settle:

/terminal:observe 2 --watch

Workflow: Check on a /terminal:watch Process

1. /terminal:watch "bun run dev"     → running in slot 1
2. ... work on other things ...
3. /terminal:observe 1               → current server output

Lost the slot number to context compaction? /terminal:observe with no argument lists them again.

Implementation

No argument: mcp__plugin_terminal_mux__list-slots(), then mcp__plugin_terminal_mux__capture-pane({ slot: 1, lines: 50 }).
Slot given: mcp__plugin_terminal_mux__capture-pane({ slot, lines: 50 }).
--watch: mcp__plugin_terminal_mux__watch-pane({ slot, triggers: "exit,error,idle:30", timeout: 120 }).
To check process state: mcp__plugin_terminal_mux__pane-state({ slot }) returns { slot, panePid, foregroundPid, foregroundCmd, isAlive, waitingForInput }.

Notes

lines: 200 reads further back into scrollback.
pane-state says whether a process is blocked, waiting for input, or dead without reading the screen.
A pane the user is working in is not a slot and cannot be read. Run the process in a slot, or read its log file.

Read the full file on GitHub · 67 lines

Changes

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 · -22 lines · +19 tokens per session a5cf7a1fa06f
1mo ago First seen · 89 lines · 28 tokens per session scan A 27ab25c72607

Subscribe to this mod's changes

observe is a command published in the GitHub repository MadAppGang/magus (13 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 680 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

DevOps and cloud Testing

prototype

You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

grainulation/grainulator · 0 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

observe