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/embedgit 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/embed)<a href="https://agentmods.dev/commands/twelvelabs-io/twelve-labs-claude-code-plugin/embed"><img src="https://agentmods.dev/badge/commands/twelvelabs-io/twelve-labs-claude-code-plugin/embed.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 | $0.00010 | $0.02194 |
| Opus 5 | $0.00005 | $0.01097 |
| Sonnet 5 | $0.00002 | $0.00439 |
| Haiku 4.5 | $0.00001 | $0.00219 |
Grade A, and why
embed 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 5d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/twelvelabs:embed - Video Embeddings
Create video embeddings from local video files or remote URLs, or check the status of embedding tasks.
Usage
/twelvelabs:embed <path-or-url> # Start a new embedding task
/twelvelabs:embed status [task-id] # Check status of a recent embedding task
/twelvelabs:embed get <task-id> # Retrieve embeddings from a ready task
/twelvelabs:embed get <index-id> <video-id> # Retrieve embeddings of an already-indexed video
User provided: $ARGUMENTS
Arguments
path-or-url- A local file path or remote URL to a video file (used to start a new embedding task).status- Check embedding task status. Optionally provide a task ID.get <task-id>- Retrieve embeddings for a completed embedding task.get <index-id> <video-id>- Retrieve embeddings of a previously-indexed video (no new task required — uses the embeddings produced during indexing).
Supported Video Formats
.mp4- MPEG-4 Video.mov- QuickTime Movie.avi- Audio Video Interleave.mkv- Matroska Video.webm- WebM Video
Examples
Create Embeddings
/twelvelabs:embed ./video.mp4
/twelvelabs:embed /absolute/path/to/video.mp4
/twelvelabs:embed https://example.com/video.mp4
Check Status
/twelvelabs:embed status
/twelvelabs:embed status 6789abcd-1234-5678-9012-abcdef123456
Instructions for Claude
When the user invokes /twelvelabs:embed, the argument is provided in $ARGUMENTS. Follow these steps:
Step 1: Parse Arguments
If $ARGUMENTS is empty:
- Display: "Please provide a video path/URL or use
statusto check tasks." - Stop processing.
Check the first token of $ARGUMENTS (case-insensitive):
status→ Status Flow (any remaining token is an optional task ID).get→ Retrieve Flow (see below). One trailing token = task ID; two trailing tokens = indexId then videoId.- anything else → Embed Flow (start a new task).
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.
- 5d ago First seen · 314 lines · 10 tokens per session scan A c667144468ce
embed 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 10 tokens to every session and 2,194 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
querying
Query documents from a search index using type-safe filters with support for pagination, sorting, field selection, scoring, and highlighting. Count matching documents efficiently without returning results.
agent-brain-index
Index documents for semantic search.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
ingest
Manually add knowledge to the Weaviate store.
web-add
Ingest a single URL into the knowledge base.
web-ingest
Crawl the configured source and generate knowledge markdown files.