transcreveai-video-intelligence

transcreveai-video-intelligence is a skill for Claude Code, Codex from DeHor-Labs/transcreve-ai. It costs 73 tokens per session (1,899 once invoked), scanned C, original, MIT.

A workflow for turning online videos or media files into organized, evidence-backed notes using TranscreveAI. It supports sources such as YouTube, TikTok, Instagram Reels, Loom, Vimeo, and X videos.

In plain words
What is it for?
Use it to inspect video sources, create summaries or knowledge dossiers, index videos for retrieval, and ask questions about their contents.
Why use it?
It removes the need to watch and manually organize long videos before using their information. It can also preserve the resulting knowledge for later searches and questions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to inspect video sources, create summaries or knowledge dossiers, index videos for retrieval, and ask questions about their contents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence
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.

Any agent
npx skills add DeHor-Labs/transcreve-ai --skill transcreveai-video-intelligence
Clone the repo
git clone --depth 1 https://github.com/DeHor-Labs/transcreve-ai

Made for: Claude Code, Codex.

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 transcreveai-video-intelligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence/github.svg)](https://agentmods.dev/skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence)
Your own site
<a href="https://agentmods.dev/skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence"><img src="https://agentmods.dev/badge/skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence/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.

agentmods 80×15 button for transcreveai-video-intelligence

Your own site · 80×15
<a href="https://agentmods.dev/skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence"><img src="https://agentmods.dev/badge/skills/dehor-labs/transcreve-ai/transcreveai-video-intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00073 $0.01899
Opus 5 $0.00036 $0.00949
Sonnet 5 $0.00015 $0.00380
Haiku 4.5 $0.00007 $0.00190

Measured 12d ago against content hash 260c91b7b3d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

transcreveai-video-intelligence scanned grade C with 1 finding 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 12d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

use `--index-db "$TMP/index.db"` and `--out "$TMP/runs"`, read the generated artifacts, then `rm -rf "$TMP"`.
plugins/transcreveai/skills/transcreveai-video-intelligence/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TranscreveAI Video Intelligence

Use this skill when the user sends a video URL/file or asks Codex to extract, summarize, analyze, index, or ask questions about video content with TranscreveAI.

Tooling Preference

  • Prefer the TranscreveAI MCP tools when available:
    • sources_probe for source pre-checks.
    • agent_run for the full probe/analyze/index/ask workflow.
    • agent_batch for saved lists of sources.
    • index, ask, runs_list, runs_show, and shared_catalog for retrieval.
  • If the MCP tools are not available in the current Codex thread, use the CLI.
  • CLI command preference:
    • First try transcreveai.
    • If it is not on PATH, use the plugin wrapper at ./scripts/transcreveai from the installed plugin root.
  • MCP server command for local registration:
    • bash ./scripts/transcreveai-mcp --transport stdio from the installed plugin root.
  • The plugin wrappers add /opt/homebrew/bin and /usr/local/bin to PATH so Homebrew FFmpeg/Tesseract installs are visible to Codex-launched processes.
  • If TranscreveAI is not installed globally, the wrappers create a venv under ~/.cache/transcreveai-codex-plugin and install transcreve-ai[mcp,rag] from pinned commit 7490586e86b57eefae377dc6839e9476f89ffd8d of https://github.com/DeHor-Labs/transcreve-ai.git.

Required Nested Handoff

Whenever TranscreveAI is used as a nested capability for another agent or workflow:

  • Keep run_id, out, and index-db identifiable for the caller.
  • Use temporary retention by default when the caller only needs extraction, summary, or an answer from YouTube, Reels, TikTok, local media, and similar sources.
  • Preserve artifacts or index in the user's real knowledge base only when the caller/user asks to save, index, audit later, or reuse the dossier.
  • When durable reuse is requested, run transcreveai share RUN_ID --json or call MCP share_run after analysis. If the run used an isolated index, pass the same --index-db or use transcreveai share --run-dir "$RUN_DIR" --json. It writes handoff.md, manifest.json, knowledge.md, and analysis.json, and updates share-root catalog.json/index.md. To rediscover durable packets later, use transcreveai share --catalog --json or MCP shared_catalog.
  • If the dossier is preserved or indexed, explicitly say: O dossie que voce criou foi salvo para voce como conhecimento.
  • Include the path to knowledge.md, the run_id, and whether the knowledge was saved in the user's real index or in an isolated agent index.
  • If the run was temporary and cleaned up, do not claim it was saved; report the run_id, that the answer was based on generated artifacts, and that temporary files were removed.

Read the full file on GitHub · 154 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. 12d ago First seen · 154 lines · 73 tokens per session scan C 260c91b7b3d5

Subscribe to this mod's changes

transcreveai-video-intelligence is a skill published in the GitHub repository DeHor-Labs/transcreve-ai (5 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,899 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

tiktok-transcribe

A workflow that downloads TikTok videos, turns their audio into text with speech-recognition software, and saves the result as a Markdown file.

chubbyguan/chubbyskills · 30 tokens

weibo-transcribe

A workflow that downloads a Weibo video, converts its speech to text with a Chinese-focused speech-recognition model, and saves the transcript as a Markdown file.

chubbyguan/chubbyskills · 27 tokens

youtube-transcribe

A tool that downloads YouTube videos or subtitles, turns speech into text, and can translate English into Chinese in a bilingual Markdown file.

chubbyguan/chubbyskills · 41 tokens

bilibili-transcribe

A workflow that downloads videos from Bilibili, a Chinese video-sharing site, transcribes their speech, and saves the result as Markdown text. It accepts Bilibili links or BV video identifiers and tries available subtitles before audio transcription.

chubbyguan/chubbyskills · 42 tokens

douyin-transcribe

A workflow for downloading Douyin videos, converting their speech to text with SenseVoice-Small, and saving the result as a Markdown file. Douyin is the Chinese short-video platform also known internationally as TikTok’s Chinese counterpart.

chubbyguan/chubbyskills · 37 tokens

frameproof

A video analysis tool that indexes speech and visible screen text in recordings from YouTube, Loom, Zoom, Kinescope, or local MP4 files. It links claims about the screen to exact frames and time codes, while reporting sections that were not visually covered.

edvardgrishin27/frameproof · 228 tokens