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 Knuckles-Team/hdhomerun-mcp --skill hdhr-discovery-opsgit clone --depth 1 https://github.com/Knuckles-Team/hdhomerun-mcpWrote 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/knuckles-team/hdhomerun-mcp/hdhr-discovery-ops)<a href="https://agentmods.dev/skills/knuckles-team/hdhomerun-mcp/hdhr-discovery-ops"><img src="https://agentmods.dev/badge/skills/knuckles-team/hdhomerun-mcp/hdhr-discovery-ops/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/knuckles-team/hdhomerun-mcp/hdhr-discovery-ops"><img src="https://agentmods.dev/badge/skills/knuckles-team/hdhomerun-mcp/hdhr-discovery-ops.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 | $0.00156 | $0.01028 |
| Opus 5 | $0.00078 | $0.00514 |
| Sonnet 5 | $0.00031 | $0.00206 |
| Haiku 4.5 | $0.00016 | $0.00103 |
Grade A, and why
hdhr-discovery-ops 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 11d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HDHomeRun Discovery Operations
Locates HDHomeRun tuner devices per https://info.hdhomerun.com/info/discovery_api — local UDP broadcast (port 65001) and the SiliconDust cloud discovery HTTP endpoint.
When to use
- You don't know a device's current IP (first-time setup, DHCP re-lease).
- Local broadcast discovery fails (client on a different VLAN/subnet from the tuner) and you need the cloud fallback.
- You want to refresh the on-disk discovery cache before a doctor run.
When NOT to use
- You already have a working device URL → go directly to
hdhr-http-api-opsorhdhr-tuner-control. - Discovering a DVR record engine (separate software/hardware, its own
discover.json) → that's documented underhdhr-dvr-ops, not here.
Prerequisites & environment
Connect via the mcp-client skill against the hdhomerun-mcp MCP server.
No credentials are required for discovery.
| Variable | Required | Notes |
|---|---|---|
DISCOVERYTOOL |
optional | Toggle this tool domain (default enabled) |
Tools & actions
| Condensed tool | Actions |
|---|---|
discovery_operations |
broadcast, targeted, cloud, cache |
Key parameters
broadcast:{"timeout": 2.0, "device_id": <int, optional wildcard match>}.targeted:{"ip": "<known ip>", "timeout": 2.0}— sends the same UDP discover packet directly to a known address (works across VLANs where broadcast doesn't).cloud:{"device_id": "<hex DeviceID, optional>"}— omit to list every device SiliconDust has ever seen register from this account/network.cache:{}— reads the last cached discovery result (used byhdhr-doctor's freshness check) without hitting the network.
Recipes (params_json)
Broadcast discovery on the local subnet:
{"action": "broadcast", "params_json": "{\"timeout\": 2.0}"}
Rediscover a device you know the (possibly stale) IP for:
{"action": "targeted", "params_json": "{\"ip\": \"10.0.132.114\"}"}
Cloud discovery by DeviceID (works across VLANs, no broadcast needed):
{"action": "cloud", "params_json": "{\"device_id\": \"10ACFCDE\"}"}
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.
- 11d ago First seen · 91 lines · 156 tokens per session scan A 5a825ddbdbef
hdhr-discovery-ops is a skill published in the GitHub repository Knuckles-Team/hdhomerun-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 156 tokens to every session and 1,028 once invoked, about $0.0008 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
meraki-network-ops
Cisco Meraki organization and network operations (read-only) — org discovery, network inventory, device inventory, clients, group policies, admins, licensing, alert settings via Cisco's official Meraki MCP. Use as the entry point for any Meraki question, to discover org and network IDs, or to inventory Meraki networks…
network-aiops
Use this skill whenever the user needs to operate a network device — read device facts, interfaces (+ counters/IP), BGP/LLDP neighbors (summary and detail), ARP/MAC tables, VLANs, routes, hardware environment (fans/temp/power/CPU/mem), optics, NTP, users, SNMP info, VRFs, and an aggregated device-health summary; run…
ha-discovery-augment
Augments an existing Home Assistant Custom Integration with one network or bus discovery mechanism beyond Zeroconf — DHCP, SSDP/uPnP, USB, HomeKit, or MQTT discovery — conforming to spec/ha/discovery-mechanisms. Sets the manifest matcher list, implements the typed asyncstep in configflow.py, forwards into a confirm…
vlan-hopping-and-trunking
Skill "vlan-hopping-and-trunking" from akashrpatil/awesome-offensive-security-skills, covering vlan hopping & trunking attacks, when to use, prerequisites, workflow and leave it running for a few minutes.
vlan-hopping-attacks
Execute VLAN Hopping attacks to bypass Layer 2 network segmentation constraints. Exploit misconfigured switch ports utilizing Switch Spoofing natively via Dynamic Trunking Protocol (DTP) and specifically Double Tagging (802.1Q) inherently to unconditionally access isolated networks natively.
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…