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 hdhomerun-mcp-developmentgit 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/hdhomerun-mcp-development)<a href="https://agentmods.dev/skills/knuckles-team/hdhomerun-mcp/hdhomerun-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/hdhomerun-mcp/hdhomerun-mcp-development/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/hdhomerun-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/hdhomerun-mcp/hdhomerun-mcp-development.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 | $0.00044 | $0.01197 |
| Opus 5.5 | $0.00018 | $0.00479 |
| Sonnet 5.5 | $0.00009 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
hdhomerun-mcp-development 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 today.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hdhomerun-mcp development
This repository owns the HDHomeRun device and cloud DVR API calls, MCP action
mapping, connector source declarations, ontology mappings, and packaged
content. The connector SDK owns shared transports, TLS policy, credential
helpers, and artifact contracts; admission and durable graph state belong to
their owning repositories. Read AGENTS.md and the focused tests before
changing a surface. Keep credentials, private endpoints, tuner records, and
generated runtime state out of source, fixtures, logs, and this skill.
Repository and runtime map
hdhomerun_mcp/__init__.pydeclares the one SDKConnector, its API facade, client factory, andhdhomerun_mcp.mcptool module. Preserve this identity and the existing stdio/HTTP serving boundary.hdhomerun_mcp/api/owns the modular HTTP, discovery, DVR, doctor, and protocol clients.hdhomerun_mcp/api_client.pyis only the compatibility facade; do not create a second client plane.hdhomerun_mcp/mcp/owns action-routed tools. Keep tool names, request and response models, device discovery, lineup, tuner, DVR, and doctor behavior aligned with the API modules.hdhomerun_mcp/auth.pyresolvesHDHOMERUN_URL,HDHOMERUN_DEVICE_AUTH,HDHOMERUN_TLS_PROFILE, andHDHOMERUN_TLS_PROFILE_REFthrough the SDK. The local tuner API is normally unauthenticated while cloud DVR recording rules use the device auth value; preserve that distinction and never disable TLS verification.hdhomerun_mcp/connector_sources.py,kg_ingest.py, andontology/hdhomerun.ttlare the source, ingestion, and ontology boundaries. Extend those declarations instead of duplicating IDs or mappings in tools.hdhomerun_mcp/skills/,ontology/,connectors/, prompts, andmcp_config.jsonare package data. Inspect a built wheel when changing packaged content.
Rapid delivery: the 5-minute contract
- Find the owning row with
git grep -n "<term>" -- specs, read this skill,AGENTS.md, and the directly bound tests before editing. - Inspect the SDK
Connector, action dispatch, API wrapper, auth/TLS path, source declarations, ingestion mapping, and package-data declaration before changing runtime or packaged content. - Make the smallest connector-owned change. Preserve public tool names and
payload schemas, HDHomeRun API paths,
HDHOMERUN_*settings, TLS verification, stable source IDs, ontology mappings, and the SDK boundary. - Run the smallest focused tests with the locked environment, then run the repository hooks normally. Never bypass a hook or failing gate.
- When packaged content changes, advance the patch version and refresh
uv.lock; inspect the wheel and sdist for the intended skill and other declared resources before publication. - Treat Pages and package publication as separate proof. After the exact main
SHA succeeds, verify
/spec-delivery/, itsindex.html, andsnapshot.jsonover HTTPS. Do not claim publication from local source inspection alone.
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.
- today First seen · 105 lines · 44 tokens per session scan A 281cb9ca43ea
hdhomerun-mcp-development is a skill published in the GitHub repository Knuckles-Team/hdhomerun-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,197 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 2026-10-27.
Other skills, from other repositories
epistemic-graph-development
Develop, build, test, and gate changes in the epistemic-graph engine repository. Use before adding a capability, changing the wire contract, or running the test/gate suite in this repo. Covers the Rust-native rule (new behaviour is a Rust crate exposed through the generated wire contract; Python/Go/JS are clients, not…
gitlab-api-development
Develop, test, gate, and release the GitLab REST and GraphQL connector. Use this skill when changing API mappings, governed MCP tools, authentication, tenant selection, KG ingestion, packaged content, or repository gates.
freshrss-agent-development
Develop, test, gate, and release the freshrss-agent connector. Use this skill when changing FreshRSS Reader API mappings, governed MCP tools, delegated or fixed authentication, KG ingestion, packaged content, or repository gates.
plugin-test
A testing guide for Zhin.js plugins using Vitest, a JavaScript and TypeScript testing framework. It focuses on checking command and tool behavior, ordinary business logic, and the plugin package’s required structure.
servicenow-api-development
Develop, test, and publish the servicenow-api connector while preserving its typed ServiceNow clients, MCP surface, packaged content, spec evidence, and shared release gates.
argos-upload
Upload a screenshot, an image or a screen recording to Argos and get a shareable URL plus ready-to-paste Markdown, so it can be embedded in a pull request, an issue, a changelog or a chat message — or attached to a branch or pull request, where Argos posts and maintains the comment itself. Use whenever you have…