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 calesthio/generative-media-skills --skill twelvelabs-video-understandinggit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/twelvelabs-video-understanding)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/twelvelabs-video-understanding"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/twelvelabs-video-understanding/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/calesthio/generative-media-skills/twelvelabs-video-understanding"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/twelvelabs-video-understanding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00167 | $0.05656 |
| Opus 5 | $0.00084 | $0.02828 |
| Sonnet 5 | $0.00033 | $0.01131 |
| Haiku 4.5 | $0.00017 | $0.00566 |
Grade A, and why
twelvelabs-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 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TwelveLabs video understanding
TwelveLabs builds video foundation models that read footage the way a human editor does — across visuals, on-screen text, motion, sound, speech, and music — and expose that understanding through a REST API, SDKs (Python, Node), an MCP server, and NLE plugins. This skill is for driving that platform to log, search, describe, segment, and tag video for production work. It is not a video generator; TwelveLabs does not synthesize or edit pixels.
All volatile facts below carry a verification date. Everything moves fast here — re-verify model names, limits, and pricing against docs.twelvelabs.io before quoting them to a user as current.
When this skill applies
Reach for TwelveLabs when the job is any of:
- Archive / footage search — "find every shot where the CEO is on stage," "clips with a red car at night," "where does someone say 'quarterly earnings'." Natural-language, image, or combined queries against indexed video.
- Logging & tagging — auto-generate loggable metadata (who/what/where/action) for raw footage or dailies.
- Segmentation — chapters, scene breaks, highlights, speaker changes, sports plays, ad-break points.
- Video-to-text — summaries, descriptions, captions, Q&A over a clip, structured JSON extraction (e.g. shot lists, compliance flags).
- Embeddings — multimodal vectors for a custom recommender, dedup, similarity, or a RAG-over-video store.
- Compliance / brand-safety review — locate logos, on-screen text, spoken phrases, or sensitive content across a library.
Do not use it to create video, apply visual effects, transcode, or as a general speech-to-text tool (it does speech understanding for search/analysis, but a dedicated ASR is cheaper if plain transcripts are all you need).
The two model families
[Documented — docs.twelvelabs.io/docs/concepts/models, verified 2026-07-10]
TwelveLabs is not one model. Pick by task:
| Marengo | Pegasus | |
|---|---|---|
| Purpose | Search + embeddings (retrieval) | Analysis + text generation |
| Output | Ranked video segments; vectors | Natural-language / structured text |
| Current version | Marengo 3.0 (GA Nov 2025) | Pegasus 1.5 (Apr 2026); 1.2 still available |
| You call it via | /search, /embed |
/analyze |
| Modalities read | visual, audio, on-screen text/OCR, logos, speech, music | visual, audio, speech, on-screen text |
What ships with it
1 file 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 · 271 lines · 167 tokens per session scan A 5d92900fa34c
twelvelabs-video-understanding is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 167 tokens to every session and 5,656 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…