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.
npx agentmods add commands/tinhtran24/maestro/previewgit clone --depth 1 https://github.com/tinhtran24/maestroWrote 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/tinhtran24/maestro/preview)<a href="https://agentmods.dev/commands/tinhtran24/maestro/preview"><img src="https://agentmods.dev/badge/commands/tinhtran24/maestro/preview.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 | $0.00000 | $0.00277 |
| Opus 5 | $0.00000 | $0.00138 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
preview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
maestro preview
Open a URL in the desktop browser panel for the current session. With no argument it opens the workspace's static entry point, falling back to this session's existing preview target when no entry point exists. A local file can be opened by its absolute file:// URL. Use maestro preview clear to empty the panel.
Syntax
maestro preview [url] [flags]
maestro preview [command]
Flags
No flags beyond -h / --help.
Subcommands
maestro preview (bare form)
Open the workspace's static entry point, or the session's existing preview target.
Examples:
# Open the default entry point for this session's workspace
maestro preview
# Open a local dev server
maestro preview http://localhost:5173
(or wherever the dev server is running)
# Open a local HTML file
maestro preview file://$(pwd)/index.html
maestro preview clear
Clear the desktop browser panel for the current session.
Syntax:
maestro preview clear [flags]
Flags:
No flags beyond -h / --help.
Examples:
# Clear the preview panel
maestro preview clear
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.
- 4d ago First seen · 63 lines · 0 tokens per session scan A 82719a01e9ee
preview is a command published in the GitHub repository tinhtran24/maestro (3 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 277 tokens. 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 2026-08-31.
Other commands, from other repositories
test-browser
Run browser tests on pages affected by current PR or branch.
reproduce-bug
Reproduce and investigate a bug using logs, console inspection, and browser screenshots.
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
e2e
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.
playbook
Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.
unschedule-playbook
Cancel a scheduled playbook routine.