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 yaniv-golan/smalltv-ultra-skill --skill geekmagic-smalltv-ultragit clone --depth 1 https://github.com/yaniv-golan/smalltv-ultra-skillWrote 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/yaniv-golan/smalltv-ultra-skill/geekmagic-smalltv-ultra)<a href="https://agentmods.dev/skills/yaniv-golan/smalltv-ultra-skill/geekmagic-smalltv-ultra"><img src="https://agentmods.dev/badge/skills/yaniv-golan/smalltv-ultra-skill/geekmagic-smalltv-ultra/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/yaniv-golan/smalltv-ultra-skill/geekmagic-smalltv-ultra"><img src="https://agentmods.dev/badge/skills/yaniv-golan/smalltv-ultra-skill/geekmagic-smalltv-ultra.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00187 | $0.03097 |
| Opus 5 | $0.00093 | $0.01548 |
| Sonnet 5 | $0.00037 | $0.00619 |
| Haiku 4.5 | $0.00019 | $0.00310 |
Grade B, and why
geekmagic-smalltv-ultra scanned grade B with 2 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 12d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
requests.post("http://{IP}/doUpload?dir=/image/", files={"file": f}) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**If the file exists:** Read the YAML frontmatter to get `device_ip`, `model`, and `firmware_version`. Use the stored IP for all commands. Still verify reachability with `curl -s http://{IP}/v.json` on first use in the s How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GeekMagic SmallTV Ultra
Control, customize, and develop firmware for the GeekMagic SmallTV Ultra — an ESP8266-based IoT device with a 240x240 TFT display, controlled entirely over HTTP with no authentication.
Device Configuration
Check for saved device settings at .claude/geekmagic-smalltv-ultra.local.md before any device interaction.
If the file exists: Read the YAML frontmatter to get device_ip, model, and firmware_version. Use the stored IP for all commands. Still verify reachability with curl -s http://{IP}/v.json on first use in the session — if it fails, inform the user the device may be offline or the IP may have changed.
If the file does not exist: Ask the user for the device IP. To find it: the IP is displayed on the device screen during boot (unplug and replug the USB-C cable — there is no battery), and also briefly shown on the default Weather Clock theme between weather data rotations. After successful verification via /v.json, create the settings file:
---
device_ip: 192.168.5.253
model: SmallTV-Ultra
firmware_version: Ultra-V9.0.43
last_verified: 2026-03-02
---
Populate model and firmware_version from the /v.json response (m and v fields). Update last_verified to the current date. This file persists across sessions so the user only provides the IP once.
If the device IP changes: Update the file with the new IP after successful verification. If the firmware version in /v.json differs from the stored value, update firmware_version in the file and inform the user (e.g., "Device firmware updated from V9.0.43 to V9.0.45 since last session").
Critical Safety Rules
No authentication exists on any endpoint. Every HTTP request executes immediately with no confirmation. Before any write operation:
- Load the device IP from
.claude/geekmagic-smalltv-ultra.local.md(or ask the user if not configured) - Verify reachability:
curl -s http://{IP}/v.json - Confirm the response contains
"m":"SmallTV-Ultra"— wrong model means wrong firmware means potential brick - Never probe write endpoints without explicit user intent
What ships with it
3 files 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.
- 12d ago First seen · 239 lines · 187 tokens per session scan B ad0c7e751a7f
geekmagic-smalltv-ultra is a skill published in the GitHub repository yaniv-golan/smalltv-ultra-skill (9 stars, last pushed 6mo ago), licensed MIT. It adds 187 tokens to every session and 3,097 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
endpoint-management
Manages laptops, desktops and mobile devices — enrollment, configuration, patching, software distribution, and lost or compromised devices. Use this to set up device management, standardize builds, roll out software or an OS upgrade, handle a lost device, or bring an unmanaged fleet under control.
ops-home
OPS on-demand: This skill should be used when the user asks to "homey", "smart home", or…
aurora
Aurora Smart Home orchestrator — routing layer for all smart home skills. Use this skill when the user asks ANY smart home question and you need to decide which skill to invoke, or when a task spans multiple skills (e.g., "build a sensor that shows on a dashboard and triggers automations"). Invoke aurora FIRST before…
ESPHome
ESPHome device configuration, firmware, and IoT product development. Covers ESP32, ESP32-S3, ESP32-C3, ESP32-C6, ESP32-H2, ESP32-P4, ESP8266, RP2040, RP2350, nRF52, LibreTiny, Shelly, Sonoff, Tuya, BLE proxy, Matter firmware, Thread, Zigbee, GPIO, sensor YAML, LVGL displays, LED strips, voice assistant hardware…
HA Integration Dev
Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.