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 jui-hung-yuan/smarthome-mcp-lab --skill light-controlgit clone --depth 1 https://github.com/jui-hung-yuan/smarthome-mcp-labWrote 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/jui-hung-yuan/smarthome-mcp-lab/light-control)<a href="https://agentmods.dev/skills/jui-hung-yuan/smarthome-mcp-lab/light-control"><img src="https://agentmods.dev/badge/skills/jui-hung-yuan/smarthome-mcp-lab/light-control/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/jui-hung-yuan/smarthome-mcp-lab/light-control"><img src="https://agentmods.dev/badge/skills/jui-hung-yuan/smarthome-mcp-lab/light-control.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 | $0.00039 | $0.00516 |
| Opus 5.5 | $0.00016 | $0.00206 |
| Sonnet 5.5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
light-control 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 2mo 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
Light Control
Controls the TAPO L530E bulb via smarthome.devices.bulb_cli. All commands output JSON.
Set TAPO_MOCK=1 to run without hardware.
Commands
# Turn on / off
uv run python -m smarthome.devices.bulb_cli turn_on
uv run python -m smarthome.devices.bulb_cli turn_off
# Brightness (1–100)
uv run python -m smarthome.devices.bulb_cli set_brightness '{"brightness": 50}'
# Color temperature in Kelvin (2500–6500)
uv run python -m smarthome.devices.bulb_cli set_color_temp '{"color_temp": 3000}'
# Named color (e.g. Lime, BlueViolet, Candlelight, AliceBlue)
uv run python -m smarthome.devices.bulb_cli set_color '{"color_name": "Candlelight"}'
# Show color palette (also sends a Slack dropdown in Slack sessions)
uv run python -m smarthome.devices.bulb_cli show_palette
# Current status
uv run python -m smarthome.devices.bulb_cli get_status
Notes
- Brightness 1–30: dim / relaxed mood
- Brightness 70–100: bright / task lighting
- Color temp 2500–3000 K: warm white (evening / movie)
- Color temp 5000–6500 K: cool daylight (focus / morning)
set_colorandset_color_tempare mutually exclusive; using one clears the other
Color Palette UX
When the user asks to change the bulb color or asks "what colors are available":
- Run
show_palette— it returns a formatted text list for you to relay, and automatically provides click buttons in Slack. Do not type the list manually. - Wait for the user to reply with a number or name.
- Run
set_colorwith the corresponding name.
If the user asks to add, remove, or replace a color in the palette, use memory_write to update the ## Light Color Palette section in USER.md.
Table format: | # | Name | Emoji | Mood |
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.
- 2mo ago First seen · 51 lines · 39 tokens per session scan A 7d3fb16cf834
light-control is a skill published in the GitHub repository jui-hung-yuan/smarthome-mcp-lab (0 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 516 once invoked, about $0.0002 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 2026-08-31.
light-control compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| light-controljui-hung-yuan/smarthome-mcp-lab | Skill | 0 | 2mo ago | MIT | A | 39 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| doca-socket-relayNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 236 | Claude Code, Codex |
| hsb-flashNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | B | 94 | Claude Code |