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 shellygit 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/shelly)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/shelly"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/shelly/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/shelly"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/shelly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 189 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 240 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 218 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 250 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00066 | $0.03509 |
| Opus 5 | $0.00033 | $0.01754 |
| Sonnet 5 | $0.00013 | $0.00702 |
| Haiku 4.5 | $0.00007 | $0.00351 |
Grade A, and why
shelly 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 9d 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.
or kernel log drops with `reason: NECP`, verify that a direct LAN `curl` from How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shelly
Use this skill for Shelly device inspection and guarded control through the
bundled helper. Keep the markdown instructions generic; API-specific request
construction belongs in shelly.cjs.
Core Contract
- Run Shelly HTTP operations through
skills/shelly/shelly.cjs. Do not handcraft Shelly URLs or JSON bodies when the helper supports the operation. - The helper executes HTTP operations through the HybridClaw gateway, so normal
Shelly reads and writes should be a single helper command. Use
--requestonly when an explicit request specification is needed for debugging or code review. For WebSocket planning outputs, use the emittedwebSocketobject as the complete connection or message specification. - Read state before any relay, switch, light, or cover control operation.
- Treat control operations as amber. Before asking for approval, build an
approval-planfor the selected operation and include itsapprovedHelperCommandTextin the approval request. Stop after presenting the plan. Only after the operator confirms in a later message, run that helper command exactly and use its emitted request specification unchanged. - Do not perform factory reset, reboot, firmware update, Wi-Fi reset, auth changes, or certificate upload through this skill.
Helper Operations
Use this command surface directly; do not rediscover flags by trial and error.
Run node skills/shelly/shelly.cjs --help only when the surface below appears
stale. The helper owns the Shelly API method, path, body selection, gateway
dispatch, secret injection, and response wrapping. Normal HTTP commands execute
the request and return command: "live", the operation, a redacted request
summary, and the gateway result. --request emits a request wrapper containing
command, operation, stakesTier, and httpRequest without executing it.
WebSocket helpers emit webSocket instead of httpRequest. approval-plan
emits no httpRequest; it validates an amber command and returns the exact
approved helper command to run after confirmation.
What ships with it
1 file 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.
- 9d ago First seen · 279 lines · 66 tokens per session scan A 6c95fbea2146
shelly is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 3,509 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
jetson-inference-mem-tune
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
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.
browser-5f5453f9
A browser sensor skill for reading, recording, and averaging sensor values. Sensor values are measurements such as motion or acceleration from a device.
browser-609362ee
A Web Bluetooth skill for discovering nearby Bluetooth devices and connecting to them from a browser. Bluetooth is a short-range wireless connection used by devices such as sensors and accessories.
m3-health
Health check — package version, installed payload, chatlog DB row count, per-agent hook state.