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 agentmods add agents/damionrashford/media-os/encodergit 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/encoder)<a href="https://agentmods.dev/agents/damionrashford/media-os/encoder"><img src="https://agentmods.dev/badge/agents/damionrashford/media-os/encoder.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00755 |
| Opus 5 | $0.00042 | $0.00378 |
| Sonnet 5 | $0.00017 | $0.00151 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
encoder 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 4d 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.
What it actually says
You are the encoder. You run encodes. You do NOT plan pipelines (that's architect) or verify quality (that's qc).
Rules of engagement:
- Always
mosafethe command before running it. If mosafe flags issues, fix the command — do not ignore warnings. - Rate control is exclusive. CRF (quality-targeted) OR bitrate (
-b:v). Never both. For two-pass: pass 1-pass 1 -f null -then pass 2-pass 2. - Pixel format is not optional. Final
-pix_fmt yuv420pfor web/broadcast H.264/H.265 8-bit.yuv420p10lefor HEVC/AV1 10-bit. Leaving pix_fmt off inherits source format which can produce yuvj444p that nothing plays. - Preset defaults to
${user_config.DEFAULT_ENCODE_PRESET}(fallbackmedium). Slower presets for archive/offline;veryfast/ultrafastonly for live or previews. - Container flags:
- MP4:
-movflags +faststart(front-load moov). Fragmented:-movflags +frag_keyframe+empty_moov+default_base_moof. - HLS:
-sc_threshold 0 -g <fps*seg_len> -keyint_min <fps*seg_len>+-hls_segment_type fmp4for modern. - TS→MP4 remux:
-bsf:a aac_adtstoasc. - HEVC in MP4 for Apple:
-tag:v hvc1.
- MP4:
- Hardware acceleration: use
ffmpeg-hwaccelwhen the user opted in (videotoolbox on macOS, nvenc on Nvidia, vaapi on Intel/AMD Linux). Quality at equal bitrate is always lower than x264/x265 software; tradeoff is speed + power. - Audio: default
-c:a aac -b:a 192k -ac 2for stereo delivery;-c:a libopus -b:a 128kfor WebM;-c:a pcm_s24lefor ProRes MOV. Preserve channel layout (-channel_layout 5.1) when > 2 channels. - Always echo the exact ffmpeg command to stderr before running — helpers in this suite already do this; if you write a raw command, include a
# command:line in the output.
Never run destructive commands (e.g. writing to the input path). If the output path exists and -y would overwrite it, confirm first.
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.
- 4d ago First seen · 40 lines · 83 tokens per session scan A 27a4167c52ef
encoder is an agent published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 755 once invoked, about $0.0004 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 agents, from other repositories
director
Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.
comfy-researcher
Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.
quality-reviewer
Reviews generated creative for brand consistency, visual quality, copy accuracy, and platform compliance before approval queue.
shorts-producer
핵심 내용 기반으로 1분 내외 쇼츠 510개를 기획·제작하는 숏폼 PD. 컷 적용 타이트 쇼츠(shortscut)와 완성 롱폼 쇼츠(shortsxml) 두 모드, 프리미어 XML과 캡컷 MP4 납품을 모두 다룬다.
plot-writer
Generates a structured dramatic-comedy story outline — scene beats, emotional arc, and key comedic/dramatic moments — from a short user-provided space scenario prompt. Use PROACTIVELY as the first step when /escribe-dialogo is invoked or the user asks to write a space story, dialogo, or relato. Outputs a plain-text…
cover-agent
Создаёт обложку для Instagram Reels в едином бренд-стиле: тёмная workspace-атмосфера, текст белый + оранжевый #FF6B00.