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/observe)<a href="https://agentmods.dev/commands/madappgang/magus/observe"><img src="https://agentmods.dev/badge/commands/madappgang/magus/observe.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00772 |
| Opus 5 | $0.00014 | $0.00386 |
| Sonnet 5 | $0.00006 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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 3d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/terminal:observe
Read-only observation of running terminal sessions. List what's active, capture pane content, and check on processes without modifying anything.
Usage
/terminal:observe
/terminal:observe {paneId}
/terminal:observe {paneId} --watch
Pane IDs use the format %N (e.g., %3) or headless:%N (e.g., headless:%0).
What It Does
- No arguments: Lists all tmux sessions/panes, captures the most active pane
- With pane ID (
%Norheadless:%N): Captures the specified pane content - With --watch flag: Uses
watch-paneto monitor until a change event fires
This is strictly read-only — it never sends keystrokes, kills sessions, or modifies state.
Examples
Check what's running:
/terminal:observe
Lists all active sessions and shows a snapshot of the most recent pane.
Check on a dev server started earlier:
/terminal:observe %3
Captures the pane to see current server output.
Read a developer's tmux pane:
/terminal:observe %5
Captures the content of a specific pane in the developer's tmux environment.
Monitor a pane until something changes:
/terminal:observe %3 --watch
Blocks via watch-pane until an error, exit, or 30s of idle activity.
Workflow: Check on a /terminal:watch Process
After starting a process with /terminal:watch, use /terminal:observe later to check its status:
1. /terminal:watch "bun run dev" → Reports ready; paneId: %3
2. ... work on other things ...
3. /terminal:observe %3 → Shows current server output
Read Existing tmux Environment
To read the developer's running terminals:
1. /terminal:observe → Lists all tmux sessions and panes
2. /terminal:observe %5 → Reads specific pane by ID
Safety: Never kill or modify the developer's tmux sessions. This command is observe-only.
Implementation
- If no argument: call
list-sessions,list-windows,list-panes; capture the active pane - If pane ID: call
capture-pane({ paneId, lines: 50 })with that pane ID - If
--watch: callwatch-pane({ paneId, triggers: "exit,error,idle:30", timeout: 120 }) - To check process state: call
pane-state({ paneId })— returns OS-level process info
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.
- 3d ago First seen · 89 lines · 28 tokens per session scan A 27ab25c72607
observe is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 772 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 2026-09-04.
Other commands, from other repositories
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…
verify
Run repository verification using the verification-loop skill.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
check-dev
Type-check a Z specification with fuzz.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.