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 skills add vNeeL-code/GHOST --skill flashlightgit clone --depth 1 https://github.com/vNeeL-code/GHOSTWrote 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/vneel-code/ghost/flashlight)<a href="https://agentmods.dev/skills/vneel-code/ghost/flashlight"><img src="https://agentmods.dev/badge/skills/vneel-code/ghost/flashlight/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vneel-code/ghost/flashlight"><img src="https://agentmods.dev/badge/skills/vneel-code/ghost/flashlight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00010 | $0.00076 |
| Opus 5.5 | $0.00004 | $0.00030 |
| Sonnet 5.5 | $0.00002 | $0.00015 |
| Haiku 4.5 | $0.00001 | $0.00008 |
Grade A, and why
flashlight 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 yesterday.
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
Turn the flashlight on or off.
Instructions
Call the run_intent tool with the following exact parameters:
- intent: flashlight
- parameters: A JSON string with the following fields:
- state: The state to set the flashlight to ('ON' or 'OFF'). String.
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.
- yesterday Changed b3f92521d281
- 1mo ago First seen · 15 lines · 10 tokens per session scan A f352cb743fdd
flashlight is a skill published in the GitHub repository vNeeL-code/GHOST (166 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 76 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
wifi
Guide an Android Agent to inspect Wi-Fi status, scan nearby Wi-Fi networks, read configured Wi-Fi entries, connect with saved or provided credentials, disconnect, forget Wi-Fi, and use Wi-Fi settings fallbacks when Android app-layer APIs cannot complete the action.
android
Senior-level Android engineering expertise for Jetpack Compose, Material 3, shared element transitions, navigation, performance, security, background work, notifications, adaptive layouts, Coil image loading, WorkManager, FCM, Baseline Profiles, R8 optimization, accessibility, coroutines and Flow, and extraordinary UI…
bluetooth
Guide an Android agent to inspect Bluetooth state, nearby, paired, and publicly visible connected devices, start pairing, and request Bluetooth enable or disable within normal Android app limits.
autofish-control
Control Android devices with Autofish via the af CLI. Use this skill when you need reliable observe-act-verify loops, ref-based tapping, overlay management, screenshots, and recovery steps.
android-adb-control
Direct control of Android physical devices and Termux environments via Android Debug Bridge (ADB).
OpenAppSkill
Guide the Android agent to open an app, and use Google Play lookup and install tools when the app is missing.