sync-analyze

sync-analyze is a command for Claude Code from twelvelabs-io/twelve-labs-claude-code-plugin. It costs 20 tokens per session (2,216 once invoked), scanned A, original, MIT.

A command that analyzes a video synchronously and returns written text or structured JSON in the same request. It can use a video ID, URL, uploaded asset, local file, or base64 data.

In plain words
What is it for?
Use it to summarize or inspect a video with an optional prompt, using a previously indexed video, an online media file, an uploaded asset, or a local file.
Why use it?
It lets you receive an analysis immediately instead of waiting for a separate job, while directing very long videos or time-based metadata work to an asynchronous command.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the twelvelabs plugin — 10 skills, 11 commands, 2 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyze
Clone the repo
git clone --depth 1 https://github.com/twelvelabs-io/twelve-labs-claude-code-plugin

Made for: Claude Code.

Or install twelvelabs, the plugin that ships this one along with the rest of its 10 skills, 11 commands, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for sync-analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyze.svg)](https://agentmods.dev/commands/twelvelabs-io/twelve-labs-claude-code-plugin/sync-analyze)
Your own site
<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>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 72625108718e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

commands/sync-analyze.md · 206 lines

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:
    • videoId of 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 videoId from 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"

Read the full file on GitHub · 206 lines

Changes

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.

  1. 6d ago First seen · 206 lines · 20 tokens per session scan A 72625108718e

Subscribe to this mod's changes

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.