A connector for Philips Hue, a smart-lighting system of connected bulbs, rooms, scenes, and sensors. It can discover Hue equipment and control lights through a Hue Bridge.

Use it to switch lights on or off, set brightness, color, or color temperature, apply lighting effects, inspect rooms and scenes, and view connected sensors and devices.

It avoids opening the Hue app for routine lighting changes. The agent can apply settings to individual lights or groups after the system is connected.

philips_hue — Skill for Claude Code and Codex by asgeirtj

About the project

System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.

asgeirtj/system_prompts_leaks · 69,759 stars · on GitHub

Install

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.

Any agent

npx skills add asgeirtj/system_prompts_leaks --skill philips-hue

Clone the repo

git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/philips-hue/github.svg)](https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/philips-hue)

Your own site

<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/philips-hue"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/philips-hue/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/philips-hue"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/philips-hue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 896 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00025	$0.00896
Opus 5.5	$0.00010	$0.00358
Sonnet 5.5	$0.00005	$0.00179
Haiku 4.5	$0.00003	$0.00090

Measured 12d ago against content hash 0d8554f50e80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

philips_hue 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 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.

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.

Meta/muse-agent/skills/philips-hue/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Philips Hue (Smart Lighting)

Purpose

Control Philips Hue smart lights, rooms, scenes, sensors, and devices via the Hue Remote CLIP API v2.

Tooling

Use:

philips-hue <subcommand> [options]

Authentication subcommands

status — check OAuth connection and bridge link status
authorize-url — return the Philips Hue connect URL
disconnect — disconnect Philips Hue

Setup subcommands

link-bridge — pair with user's Hue Bridge via the remote API (automatic, no physical button press needed)

Discovery subcommands

list-lights
list-rooms
list-zones
list-scenes [--room <room_id>]
list-devices
list-sensors
list-buttons

Control subcommands

light --id <id> --on|--off
light --id <id> --brightness <0-100>
light --id <id> --color <hex> — e.g. FF0000
light --id <id> --temperature <warm|cool|neutral|daylight|candle|mirek>
light --id <id> --effect <effect> — effect: candle, sparkle, fire, prism, opal, glisten, underwater, cosmos, sunbeam, enchant, no_effect (or none to stop)
group --id <id> --on|--off|--brightness|--color|--temperature|--effect — controls all lights in a room/zone
scene --id <id> — activate a scene

User Onboarding

When a user first asks to set up or use Philips Hue:

Step 1 — Check Status

Run philips-hue status silently. If ready: true, skip to Step 4.

Step 2 — Connect Philips Hue

If not connected, use the connect_url from philips-hue status. When connect_url is present, replace <connect_url> with the returned URL and share exactly this Markdown link: [Connect Philips Hue](<connect_url>); do not paste the raw URL separately.

Tell the user: "Click here to sign into your Philips Hue account. Make sure to use the same account your Hue Bridge is registered to."

After they confirm, run philips-hue status again to verify.

Step 3 — Bridge Linking

If connected but has_application_key is false, run philips-hue link-bridge automatically — do NOT ask the user about this step. It is seamless and requires no physical button press. Confirm with a status check.

Read the full file on GitHub · 76 lines

Files

What ships with it

2 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.

Changes

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 · 76 lines · 25 tokens per session scan A 0d8554f50e80

Subscribe to this mod's changes

philips_hue is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,759 stars, last pushed yesterday), licensed CC0-1.0. It adds 25 tokens to every session and 896 once invoked, about $0.0001 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 2026-10-05.

Claude Code Hardware and IoT ai anthropic chatbot chatgpt claude

philips_hue