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 DeHor-Labs/transcreve-ai --skill transcreveai-video-intelligencegit clone --depth 1 https://github.com/DeHor-Labs/transcreve-aiWrote 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/dehor-labs/transcreve-ai/transcreveai-video-intelligence)<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.
<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>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 | $0.00073 | $0.01899 |
| Opus 5 | $0.00036 | $0.00949 |
| Sonnet 5 | $0.00015 | $0.00380 |
| Haiku 4.5 | $0.00007 | $0.00190 |
Grade C, and why
transcreveai-video-intelligence scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
use `--index-db "$TMP/index.db"` and `--out "$TMP/runs"`, read the generated artifacts, then `rm -rf "$TMP"`. 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_probefor source pre-checks.agent_runfor the full probe/analyze/index/ask workflow.agent_batchfor saved lists of sources.index,ask,runs_list,runs_show, andshared_catalogfor 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/transcreveaifrom the installed plugin root.
- First try
- MCP server command for local registration:
bash ./scripts/transcreveai-mcp --transport stdiofrom the installed plugin root.
- The plugin wrappers add
/opt/homebrew/binand/usr/local/binto 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-pluginand installtranscreve-ai[mcp,rag]from pinned commit7490586e86b57eefae377dc6839e9476f89ffd8dofhttps://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, andindex-dbidentifiable 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 --jsonor call MCPshare_runafter analysis. If the run used an isolated index, pass the same--index-dbor usetranscreveai share --run-dir "$RUN_DIR" --json. It writeshandoff.md,manifest.json,knowledge.md, andanalysis.json, and updates share-rootcatalog.json/index.md. To rediscover durable packets later, usetranscreveai share --catalog --jsonor MCPshared_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, therun_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.
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.
- 12d ago First seen · 154 lines · 73 tokens per session scan C 260c91b7b3d5
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.
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.
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.
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.
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.
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.
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.