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 shu-bamma/marlin-cli --skill video-understandinggit clone --depth 1 https://github.com/shu-bamma/marlin-cliWrote 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/shu-bamma/marlin-cli/video-understanding)<a href="https://agentmods.dev/skills/shu-bamma/marlin-cli/video-understanding"><img src="https://agentmods.dev/badge/skills/shu-bamma/marlin-cli/video-understanding.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 5.1 | $0.00101 | $0.01535 |
| Opus 5 | $0.00051 | $0.00767 |
| Sonnet 5 | $0.00020 | $0.00307 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
video-understanding 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 8d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-understanding — Marlin-2B as eyes on a video
Two verbs, each on a single clip, each --json:
| Job | Command |
|---|---|
| Describe a video | marlin caption <video> --json |
| Describe (one paragraph) | marlin caption <video> --detail --json |
| Find when X happens | marlin find <video> "<query>" --json |
caption = what's in it (a scene description + a <start>–<end> event timeline).
find = when one thing happens (a single start → end span).
Hard limits — read before using
- One call sees ~2 minutes. Marlin samples ~2 fps up to ~240 frames, so a single
caption/findonly "sees" a bounded clip. On longer videos the timestamps drift and detail is lost. - Longer than ~2 min → window it. Cut overlapping windows with ffmpeg, run per window, then offset the returned timestamps by the window's start:
Every timestamp fromffmpeg -i long.mp4 -ss 0 -t 120 -c copy w0.mp4 # 0–120s ffmpeg -i long.mp4 -ss 110 -t 120 -c copy w1.mp4 # 110–230s (10s overlap) marlin caption w0.mp4 --json ; marlin caption w1.mp4 --jsonw1must have110added back. findreturns ONE span — there is no multi-find. It gives the single best match. To find every occurrence, window the video (as above) and runfindper window, then collect the hits. Never assume onefindcall surfaces all matches.- Visual only. These modes don't read audio/speech. For "what was said," use a transcription tool.
- No library search. Searching across a whole folder of videos is not in these verbs (that's the experimental
index/search, not shipped — see the repo roadmap).
Resolution & memory (automatic)
Marlin's per-frame budget is ~200K pixels (≈448², 2 fps). The CLI auto-downscales the clip to that budget before inference — mirroring the model's own smart_resize — so a 1080p/4K clip is decoded small: much faster and far less memory, with no accuracy loss (the model would resize to this anyway, just after a costly full-res decode that can OOM a laptop). You don't have to do anything; it's on by default.
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.
- 8d ago First seen · 97 lines · 101 tokens per session scan A df702fd8482a
video-understanding is a skill published in the GitHub repository shu-bamma/marlin-cli (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,535 once invoked, about $0.0005 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.