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 damionrashford/media-os --skill decklink-docsgit clone --depth 1 https://github.com/damionrashford/media-osWrote 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/damionrashford/media-os/decklink-docs)<a href="https://agentmods.dev/skills/damionrashford/media-os/decklink-docs"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/decklink-docs/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/damionrashford/media-os/decklink-docs"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/decklink-docs.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 | $0.00195 | $0.02323 |
| Opus 5 | $0.00097 | $0.01162 |
| Sonnet 5 | $0.00039 | $0.00465 |
| Haiku 4.5 | $0.00019 | $0.00232 |
Grade A, and why
decklink-docs 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decklink Docs
Context: $ARGUMENTS
Quick start
- Find an API / interface / BMD enum: → Step 2 (
search --query <term>) - Read one full section: → Step 3 (
section --page <name> --id <anchor>) - Grab the whole page: → Step 4 (
fetch --page <name>) - Prime the cache offline: → Step 5 (
index) - Verify the ffmpeg
decklinkdevice options: → search on pageffmpeg-devices
When to use
- User asks "what does
IDeckLinkInput::StartStreamsreturn?" or "what pixel formats does a Mini Recorder accept?" - Need to verify an interface / method / enum exists before recommending C++ / COM code.
- Need the exact ffmpeg
-f decklinkoption list (the ffmpeg decklink demuxer / muxer docs). - Need to cite the canonical Blackmagic SDK URL in a response.
- Before writing any non-trivial DeckLink integration, check the current doc for the interface you're using.
Step 1 — Know the page catalog
The script only works against a fixed list of known Blackmagic / related doc pages. Get the list:
uv run ${CLAUDE_SKILL_DIR}/scripts/decklinkdocs.py list-pages
The catalog groups into four areas:
| Page family | What's covered |
|---|---|
blackmagic-developer / blackmagic-capture-playback |
Landing pages. The SDK ZIP is login-gated; URLs are catalog stubs. |
ffmpeg-devices-decklink / ffmpeg-devices |
The ffmpeg decklink demuxer + muxer (options, examples). |
decklink-sdk-readme-* |
Third-party mirrors of SDK sample names + API index (informational only). |
bmdtools-github |
Third-party bmdtools (the tool that ships bmdcapture / bmdplay). |
Read references/catalog.md for the full page list with descriptions and login-gated notes.
Step 2 — Search first (default workflow)
When the user names an interface, enum, method, or option, search across all pages:
uv run ${CLAUDE_SKILL_DIR}/scripts/decklinkdocs.py search --query "IDeckLinkInput" --limit 5
Scope to a page for less noise:
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.
- 9d ago First seen · 192 lines · 195 tokens per session scan A 63fa73c1a2c1
decklink-docs is a skill published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 195 tokens to every session and 2,323 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
endpoint-management
Manages laptops, desktops and mobile devices — enrollment, configuration, patching, software distribution, and lost or compromised devices. Use this to set up device management, standardize builds, roll out software or an OS upgrade, handle a lost device, or bring an unmanaged fleet under control.
keenetic-segments
Use when creating an isolated network on a Keenetic - a guest network, an IoT network, a segment routed through a VPN - explains why the obvious way produces a working network the web interface refuses to list, and the VLAN it is actually missing.
keenetic-rci
Use when a Keenetic question is not covered by the curated tools and you need rcicall - explains the RCI tree, the paths that exist, the responses that will blow up your context, and the traps that make a wrong call look like success.
keenetic-safe-changes
Use before changing anything on a Keenetic router - explains that changes are not saved until asked, what the router's fail-safe does and does not protect against, and the order that avoids locking yourself out.
keenetic-troubleshoot
Use when someone reports the internet is down, Wi-Fi is bad, a device cannot connect, or the network is slow on a Keenetic router - an ordered playbook that narrows the fault instead of guessing.