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 commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyzegit clone --depth 1 https://github.com/twelvelabs-io/twelve-labs-claude-code-pluginWrote 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/commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyze)<a href="https://agentmods.dev/commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyze"><img src="https://agentmods.dev/badge/commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyze.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 | $0.00020 | $0.02216 |
| Opus 5 | $0.00010 | $0.01108 |
| Sonnet 5 | $0.00004 | $0.00443 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade A, and why
sync-analyze 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 6d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/twelvelabs:sync-analyze - Synchronous Video Analysis
Synchronously analyse a video and return the generated text (or structured JSON) inline. Accepts a previously-indexed videoId, a direct http(s) URL, a previously-uploaded asset ID, a local file path (auto-uploaded as an asset), or base64 data.
For very long videos (>1 hour) or for time-based metadata segmentation, use /twelvelabs:async-analyze instead.
Usage
/twelvelabs:sync-analyze <video-id-or-url-or-path-or-asset-id> [prompt]
/twelvelabs:sync-analyze [prompt] # if no input given, prompts you to pick a videoId
User provided: $ARGUMENTS
Arguments
- First positional — one of:
videoIdof a previously-indexed video (Pegasus 1.2 only — see model policy below)- Direct http(s) URL to a raw media file
- Asset ID (24-char hex, or
asset_*) from a previous/twelvelabs:assets upload - Absolute or relative local file path (auto-uploaded as an asset internally)
prompt— Optional. What you want the analysis to produce. If omitted, a default summary prompt is used.
Model Policy
The MCP server supports two generative models:
- Pegasus 1.5 (default for direct inputs) — clip windowing, structured prompts with reference images, larger token budget.
- Pegasus 1.2 (legacy) — required when input is a
videoIdfrom an existing index. Mostly there for backwards compatibility.
This command picks the model automatically:
| Input type | Default modelName |
|---|---|
videoId (from existing index) |
pegasus1.2 (forced — the MCP rejects 1.5 + videoId) |
| URL / asset ID / local file / base64 | pegasus1.5 |
Override only when the user explicitly asks (e.g. "use pegasus 1.2", "legacy model"). Otherwise the defaults above apply.
Examples
/twelvelabs:sync-analyze 6a04abc... # videoId, Pegasus 1.2
/twelvelabs:sync-analyze https://example.com/clip.mp4 "summarise"
/twelvelabs:sync-analyze ./video.mp4 "what animal is shown" # auto-uploads file as asset, Pegasus 1.5
/twelvelabs:sync-analyze asset_6a04xyz... "extract action items"
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.
- 6d ago First seen · 206 lines · 20 tokens per session scan A 72625108718e
sync-analyze is a command published in the GitHub repository twelvelabs-io/twelve-labs-claude-code-plugin (23 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 2,216 once invoked, about $0.0001 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 commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.