Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MadAppGang/magusnpx agentmods add commands/madappgang/magus/watchWrote 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/watch)<a href="https://agentmods.dev/commands/madappgang/magus/watch"><img src="https://agentmods.dev/badge/commands/madappgang/magus/watch.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 | $0.00038 | $0.00806 |
| Opus 5 | $0.00019 | $0.00403 |
| Sonnet 5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
watch 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:watch
Start a long-running process, monitor it for readiness or failure, and report the result. The session stays alive for later observation.
Usage
/terminal:watch {command}
Examples
/terminal:watch "bun run dev"
/terminal:watch "npm run dev"
/terminal:watch "bun test --watch"
/terminal:watch "npm test -- --watch"
/terminal:watch "tail -f /var/log/app.log"
/terminal:watch "docker-compose up"
/terminal:watch "go run ./cmd/server"
What It Does
- Starts the given command via
start-and-watch - Monitors using a single blocking call — no polling loop required
- Uses start-and-watch — a single call that blocks until a readiness trigger fires, sending progress notifications during the wait. No polling loop.
- Reports the status: ready, errored, or still starting
- Keeps the session alive — reports the pane ID for later use with
/terminal:observe
Agentic Watch Strategy
A single call to start-and-watch handles all monitoring:
mcp__tmux__start-and-watch({
command: "<user_command>",
pattern: "<readiness_regex>",
triggers: "exit,error",
mode: "quick",
timeout: 60
}) → WatchResult
Pattern Selection by Command Type
| Command type | Pattern |
|---|---|
| Bun/Node dev server | "Local:.*http|listening on|ready in" |
| Go server | "listening on|started on|server running" |
| Test watcher (Vitest/Jest) | "press a to rerun|Waiting for file changes" |
| Bun test watcher | "watch mode|watching" |
| docker-compose up | "healthy|started" |
| Log tail | (no pattern needed — use paneId + watch-pane instead) |
Reading WatchResult
| event value | Meaning | Next action |
|---|---|---|
"pattern:..." |
Readiness pattern matched | Report ready; save paneId |
"error" |
Error output detected | Report error; show WatchResult.output |
"exit" |
Process exited | Check exitCode in paneState |
"timeout" |
No signal in timeout_secs | Report "still starting"; save paneId |
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 · 38 tokens per session scan A 4d74ec80e282
watch is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 806 once invoked, about $0.0002 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.