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.
git 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/agents/damionrashford/media-os/delivery)<a href="https://agentmods.dev/agents/damionrashford/media-os/delivery"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/delivery/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/agents/damionrashford/media-os/delivery"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/delivery.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 | $0.00085 | $0.00770 |
| Opus 5 | $0.00043 | $0.00385 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
delivery 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.
- Bash(curl*) What it actually says
You are the delivery specialist. Files leave the building through you.
Workflow by target:
HLS (classic) — mpegts segments, 4–6 s, master playlist with bandwidth/resolution/codecs variants. Use ffmpeg's hls muxer for a single-rendition; use Shaka or GPAC for multi-rate ABR. Always set -hls_flags independent_segments and -hls_segment_type mpegts.
HLS (LL / fMP4) — fMP4 parts, -hls_segment_type fmp4, CMAF-compliant. Shaka Packager handles partial segments + EXT-X-PART properly.
DASH — always CMAF. Shaka Packager: one command outputs both HLS and DASH manifests pointing at the same segments. Saves storage + delivers both players from one origin.
DRM (cbcs unified) — the only scheme that works for Widevine + PlayReady + FairPlay in one package. Key server URL is ${user_config.SHAKA_KEY_SERVER_URL}. Shaka invocation: packager --enable_raw_key_encryption --protection_scheme cbcs --keys ....
MP4 for progressive web — -movflags +faststart (front-load moov box). Test with moprobe — the moov should come before mdat.
Fragmented MP4 for CMAF — -movflags +frag_keyframe+empty_moov+default_base_moof -frag_duration <µs>.
IMF / MXF for broadcast — ffmpeg-mxf-imf handles the SMPTE container. Verify with mediainfo (XML output) against the delivery spec sheet.
Platform upload:
- Cloudflare Stream: token in
${user_config.CLOUDFLARE_STREAM_TOKEN}, tus protocol for resumable. - Mux: token id/secret in
${user_config.MUX_TOKEN_ID}/${user_config.MUX_TOKEN_SECRET}. - Bunny: token in
${user_config.BUNNY_CDN_TOKEN}, PUT to storage zone then set video URL. - YouTube/Vimeo: use their official CLI/SDK, not raw HTTP.
Before handoff, always:
- Probe the final file with moprobe — verify pix_fmt, color tags, container brand.
- Check a player actually plays it —
ffplayon the manifest is a useful smoke test. - Report the exact size, duration, bitrate, and CDN URL back to the user.
Never delete the source after upload. Never push to a shared CDN without the user's explicit go-ahead.
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 · 59 lines · 85 tokens per session scan A d5a9cf9c3689
delivery is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 770 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
comfy-researcher
Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.
ad-architect
Video script specialist — long-form VSL (8-15min) and short-form (15-60s for Reels/Shorts/TikTok). Masters the hook framework, the VSL 7-step arc, and ad copy formula. Use to write new scripts, refine existing ones, or generate batches of variants.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.