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 conow-labs/agent-skills --skill conow-devicegit clone --depth 1 https://github.com/conow-labs/agent-skillsWrote 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/conow-labs/agent-skills/conow-device)<a href="https://agentmods.dev/skills/conow-labs/agent-skills/conow-device"><img src="https://agentmods.dev/badge/skills/conow-labs/agent-skills/conow-device/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/conow-labs/agent-skills/conow-device"><img src="https://agentmods.dev/badge/skills/conow-labs/agent-skills/conow-device.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 | $0.00240 | $0.06186 |
| Opus 5 | $0.00120 | $0.03093 |
| Sonnet 5 | $0.00048 | $0.01237 |
| Haiku 4.5 | $0.00024 | $0.00619 |
Grade A, and why
conow-device 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conow Device Skill (Generic + Energy)
This skill exposes per-device end-user APIs through a single CLI. The same sk- Bearer token can address both Tuya generic devices and Conow energy devices; the CLI internally calls GET /v1.0/end-user/energy/devices/topo and GET /v1.0/end-user/energy/devices/protocol to decide which branch to use, so callers do not need to make that decision themselves.
Basic Information
- Authentication: Via Header
Authorization: Bearer {Api-key} - Credentials: Read from environment variable
CONOW_API_KEY. Base URL is auto-detected from the API key prefix. Override withCONOW_BASE_URLif needed. - API Reference: See
references/device_routing.md - Energy device control (confirm gate): See
references/device_control_confirm.md - Python CLI: See
scripts/conow_device_cli.py
Environment Variable Configuration
export CONOW_API_KEY="your-conow-api-key"
# CONOW_BASE_URL is optional — auto-detected from the sk- key prefix.
# Set it only if your deployment provides a dedicated gateway URL, e.g.:
# export CONOW_BASE_URL="https://openapi.tuyaeu.com"
| Env var | Flag | Purpose |
|---|---|---|
CONOW_API_KEY |
--api-key |
Required. Bearer token starting with sk-. |
CONOW_BASE_URL |
--base-url |
Override gateway URL. |
CONOW_DEVICE_ID |
--dev-id |
Optional. Default devId for device commands (overridden by --dev-id). |
The skill will not load if CONOW_API_KEY is missing. Never echo the raw key back to the user.
Routing Boundaries
| Scope | Handling |
|---|---|
| Account/home device inventory, single device status, control, Thing Model, topology, protocol, alarms, device indicators | Use this skill |
| Home-level consumption, generation, indicator aggregate/trend, tariff, forecast, or AI dispatch schedule | Out of scope for this device skill |
What ships with it
3 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.
- 9d ago First seen · 302 lines · 0 tokens per session scan A 9163ef7659a7
conow-device is a skill published in the GitHub repository conow-labs/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 240 tokens to every session and 6,186 once invoked, about $0.0012 per session on Opus 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.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.