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/agentlas-ai/agentlas-desktop/startupgit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/startup)<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-desktop/startup"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-desktop/startup.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 | $0.00320 |
| Opus 5 | $0.00000 | $0.00160 |
| Sonnet 5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
startup 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.
What it actually says
/startup
Always open the Startup Studio GUI first — on every invocation, before anything else. Do not gate this on whether the founder asked for a "visual workflow"; the command itself is the GUI entrypoint.
Input:
/startup <optional idea or founder workflow request>
Step 1 — launch the GUI (always)
Run this in the background so the session is not frozen by the blocking server (it auto-opens the browser after ~0.6s):
python3 scripts/open-studio-gui.py &
The launcher guarantees the GUI via a four-tier fallback ending in a page
embedded in the .py itself — it needs only python3 (no node, npm, build,
or network), so it must appear even on a fresh install where the packager
stripped the built web/dist and static webapp/*.html. Skip only on an
explicit --no-gui flag or a headless/non-interactive runtime. If python3 is
missing or the launcher errors, say so — do not claim the GUI opened.
Step 2 — route if a request was given
If the founder also provided a complete request, route it through the Startup
orchestrator (agents/00-startup-orchestrator/agent.md) across the Startup HQs
and return a founder-ready Founder Execution Packet. If no request was given,
the GUI is the workflow surface — tell the founder it is up and wait for input.
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 · 35 lines · 0 tokens per session scan A aaab9cb34348
startup is a command published in the GitHub repository agentlas-ai/agentlas-desktop (5 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 320 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
app
Control macOS apps via peekaboo app.
mcp
Run Peekaboo as an MCP server via peekaboo mcp.
set-value
Set accessibility element values directly via peekaboo set-value.
merge-and-status
Merge the current PR, pull main, surface any open contributor PRs and untriaged contributor issues, and show open milestone issues.
frontend-check
在 agent-gui UI 改动后执行。先 Read skill：.cursor/skills/quicker-agent-gui-frontend/SKILL.md。.
fix
Describe a computer problem in your own words — get a diagnosis first, then choose from clearly-explained fix options.