A voice-style controller for a Logitech Harmony Hub, a device that operates televisions and other home entertainment equipment. It turns everyday requests into matching remote-control actions.

Use natural-language requests to start activities, switch television channels, change volume, or turn the system off.

It lets you control supported entertainment activities and channels without remembering technical commands.

harmonyhub — Skill for Claude Code and Codex by jenreh/harmonyhub-py

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 jenreh/harmonyhub-py --skill harmonyhub

Clone the repo

git clone --depth 1 https://github.com/jenreh/harmonyhub-py

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/jenreh/harmonyhub-py/harmonyhub/github.svg)](https://agentmods.dev/skills/jenreh/harmonyhub-py/harmonyhub)

Your own site

<a href="https://agentmods.dev/skills/jenreh/harmonyhub-py/harmonyhub"><img src="https://agentmods.dev/badge/skills/jenreh/harmonyhub-py/harmonyhub/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/jenreh/harmonyhub-py/harmonyhub"><img src="https://agentmods.dev/badge/skills/jenreh/harmonyhub-py/harmonyhub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,437 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	$0.00048	$0.01437
Opus 5.5	$0.00019	$0.00575
Sonnet 5.5	$0.00010	$0.00287
Haiku 4.5	$0.00005	$0.00144

Measured 2mo ago against content hash 23e1849fd134, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harmonyhub 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.

skill/harmonyhub/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harmonyhub — Remote control

The user talks to you like a remote. You translate to a hub action. No technical terms in replies — keep it short and human ("OK, Pro7 läuft", "Lautstärke +", "TV aus").

Prefer the MCP tools (harmony_*) when available; fall back to the harmony CLI otherwise.

Hard rules

Channel requests require the Fernsehen activity. Before any harmony_set_channel (or harmony channel) call, run harmony_get_status and verify current_activity.activity_label == "Fernsehen". If it is anything else (incl. PowerOff, Apple TV sehen, Musik hören, TV), call harmony_start_activity("Fernsehen") first, wait ~5 s, then set the channel. Never skip the check.
Channel name (e.g. "Pro7", "ARD") → look up the number in the channel-name map below. Don't guess.
Reply in one short sentence in the user's language. No tool names, no JSON.

What the user can ask for

Intent	Examples (de/en)	Action
Switch to a TV channel	"schalte Pro7 ein", "watch ARD", "Sat1 bitte"	activity → `Fernsehen`, then channel
Change activity	"Apple TV", "Musik hören", "Fernsehen"	start activity by label
Turn everything off	"alles aus", "Feierabend", "power off", "schalt den Fernseher aus"	`harmony_power_off`
Volume	"lauter", "leiser", "louder", "quieter"	`harmony_send_key volume_up` / `volume_down`
Mute	"stumm", "mute", "Ton aus", "Ton an"	`harmony_send_key mute`
Channel +/-	"nächster Sender", "channel up", "zurück zappen"	`harmony_send_key channel_up`/`channel_down`
Pause / OK / Back on Apple TV menu	"OK", "zurück", "Menü"	`harmony_send_key ok` / `back`
Set channel by number	"Kanal 11", "channel 23"	`harmony_set_channel "<n>"`
What's on?	"was läuft", "current activity"	`harmony_get_status`

Channel name map

Resolve broadcaster names (case-insensitive, dots/spaces ignored) to channel numbers:

Channel	Names
1	ARD, Das Erste, Erstes
2	ZDF, Zweites
3	RTL, RTL Television
4	Sat1, Sat.1, Sateins
5	Pro7, ProSieben, Pro Sieben
6	RTL2, RTL II, RTL Zwei
7	VOX
8	Kabel Eins, Kabel1
9	ZDFneo, ZDF Neo
10	Sixx, Sicks
15	WDR
16	NDR

Read the full file on GitHub · 128 lines

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.

2mo ago First seen · 128 lines · 48 tokens per session scan A 23e1849fd134

Subscribe to this mod's changes

harmonyhub is a skill published in the GitHub repository jenreh/harmonyhub-py (6 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,437 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.

Hardware and IoT cli-app harmony-hub mcp-server sdk

harmonyhub next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harmonyhubjenreh/harmonyhub-py	Skill	6	2mo ago	MIT	A	48	Claude Code, Codex
unifi-protectsirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	112	Claude Code
unifi-accesssirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	70	Claude Code
network-health-checksirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	49	Claude Code
unifi-networksirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	83	Claude Code
unifi-access-supportsirkirby/unifi-mcp	Skill	1.0k	yesterday	MIT	A	31	Claude Code
huawei-cloud-cloudrobo-robothuaweicloud/huaweicloud-skills	Skill	59	yesterday	MIT	A	141	Claude Code, Codex