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 skills/ap3x-dev/ag3nt/app-launchernpx skills add AP3X-Dev/AG3NT --skill app-launchergit clone --depth 1 https://github.com/AP3X-Dev/AG3NTWrote 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/skills/ap3x-dev/ag3nt/app-launcher)<a href="https://agentmods.dev/skills/ap3x-dev/ag3nt/app-launcher"><img src="https://agentmods.dev/badge/skills/ap3x-dev/ag3nt/app-launcher.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 | $0.00023 | $0.00742 |
| Opus 5 | $0.00012 | $0.00371 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
app-launcher 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- app-launcher — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Launcher Skill
This skill provides application control on the local system. It can launch applications, open URLs, and manage running processes.
⚠️ Security Note
Launching applications requires user approval. The agent will pause and ask for confirmation before:
- Starting any application
- Opening URLs (to prevent phishing)
- Focusing/switching to applications
When to Use
- User asks to "open" or "launch" an application
- User wants to open a URL in their browser
- User asks what applications are running
- User wants to switch to a specific application
Available Commands
Launch Application
Launch an application by name.
python scripts/app_control.py launch "notepad"
python scripts/app_control.py launch "Visual Studio Code"
python scripts/app_control.py launch "chrome"
Common app names:
- Windows: notepad, calc, explorer, cmd, powershell, code, chrome, firefox
- macOS: Safari, Finder, Terminal, "Visual Studio Code", Notes
- Linux: firefox, nautilus, gnome-terminal, code
Open URL
Open a URL in the default browser.
python scripts/app_control.py url "https://example.com"
python scripts/app_control.py url "https://github.com"
List Running Applications
Show currently running applications (not all processes).
python scripts/app_control.py list
python scripts/app_control.py list --all # Include background processes
Focus Application
Bring an application window to the foreground.
python scripts/app_control.py focus "notepad"
python scripts/app_control.py focus "chrome"
Platform Support
| Operation | Windows | macOS | Linux |
|---|---|---|---|
| Launch | ✅ start |
✅ open -a |
✅ Various |
| Open URL | ✅ webbrowser |
✅ webbrowser |
✅ webbrowser |
| List apps | ✅ tasklist |
✅ ps |
✅ ps |
| Focus | ⚠️ Limited | ✅ AppleScript | ⚠️ Limited |
Notes
- App names are case-insensitive on Windows
- On macOS, use the full app name (e.g., "Visual Studio Code")
- Focus functionality may be limited depending on OS security settings
- Some apps may take a moment to start
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 116 lines · 23 tokens per session scan A 92c86b419237
app-launcher is a skill published in the GitHub repository AP3X-Dev/AG3NT (9 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 742 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 2026-08-31.
Other skills, from other repositories
app-launcher
Launch applications, open URLs in browser, and list running processes. Requires approval for launching applications.
file-manager
Open files with default applications, reveal files in explorer/finder, and search for files on the system. Requires approval for operations outside workspace.
system-info
Get system information including CPU usage, memory, disk space, battery status, and network info. Read-only and safe to use.
camera-capture
Capture images from device camera. Currently a placeholder - camera support depends on device capabilities.
voice-tts
Text-to-speech output for voice responses. Uses pyttsx3 for local TTS on supported systems.
schedule_manage
Tool: schedulemanage. All ops use action field.