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 HybridAIOne/hybridclaw --skill homematicgit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/homematic)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/homematic"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/homematic/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/hybridaione/hybridclaw/homematic"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/homematic.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 | $0.00024 | $0.02834 |
| Opus 5 | $0.00012 | $0.01417 |
| Sonnet 5 | $0.00005 | $0.00567 |
| Haiku 4.5 | $0.00002 | $0.00283 |
Grade A, and why
homematic scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
8. Do not use shell `curl`, ad hoc WebSocket scripts, or cleartext headers when How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Homematic
Use this skill for Homematic IP Home Control Unit (HCU) state inspection and guarded smart-home control planning. The primary v1 integration target is the official Homematic IP Connect API, which exposes HCU plugin communication over WebSocket. Treat CCU/RaspberryMatic and Homematic IP Access Point cloud support as separate compatibility paths until their protocols are implemented and tested.
This v1 targets remote HCU Connect API clients. The HTTPS port 6969 auth
helpers implement the remote-client enrollment flow. Installed HCU plugin
containers instead receive their token from the HCU container environment and
mounted /TOKEN file; this helper does not implement container installation.
Safety Rules
- Start with
plan,summarize-fixture,plugin-ready,get-state, orget-system-state. - For HCU setup, generate gateway
http-requestpayloads with the helper. Never ask the operator to paste activation keys or auth tokens into chat. - For HCU WebSocket operations, use helper
websocket-messageoutput as the source of truth for connection headers, message type, path, stakes tier, and approval requirement. - For a local operator-owned read-only smoke test,
run-websocketcan open the HCU WebSocket directly usingHOMEMATIC_HCU_AUTH_TOKENfrom the helper environment. Do not pass that token as an argument. Use gateway-managed execution for any amber/red operation. - Reads are green but still privacy-sensitive because home occupancy, alarms, temperatures, shutters, and energy state can reveal living patterns.
- Mutating device or group actions are amber unless they affect alarms, security zones, locks, or safety state; those are red.
- Do not execute a write unless the operator granted the exact helper-reported
requiredGrant. Include device/group ids, channel index, target value, rollback, and expected physical effect in the approval text. - Do not use shell
curl, ad hoc WebSocket scripts, or cleartext headers when the gateway tool or helper output can express the request.
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.
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 · 295 lines · 24 tokens per session scan A a281935540db
homematic is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,834 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
lilbee-mcp-wiki
Wiki layer for lilbee. Use only when the user explicitly asks about wiki / concept / entity / synthesis pages, or when lilbeestatus shows a built wiki. Requires the lilbee-mcp skill to be active for the underlying MCP connection.
m3-health
Health check — package version, installed payload, chatlog DB row count, per-agent hook state.
m3-help
List all m3-memory slash commands / skills and what they do.
continuum-recipes
Copy-pasteable Continuum patterns — RAG, plan-and-execute, ReAct, multi-tenant agents, FastAPI integration, structured output, prompt-injection scanning, custom containers. Invoke when the user asks "how do I do X with Continuum" and X is a common app pattern rather than a single API question.
m3-forget
Delete a memory permanently. Asks for confirmation first.