levea-video-editing

levea-video-editing is a skill for Claude Code, Codex from brajendrak00068/agentic-ai-video-production. It costs 33 tokens per session (494 once invoked), scanned A, original, MIT.

A guide for editing video with Levea's automated editor. It covers cuts, reframing, captions, overlays, audio changes, color work, and exporting a verified MP4 file.

In plain words
What is it for?
Use it to trim videos, make vertical clips, add captions or graphics, clean audio, sync multicamera footage, add music or voiceover, and export the result.
Why use it?
It explains how to submit an edit, continue work on the same project, wait for rendering, and handle approval or failure states.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to trim videos, make vertical clips, add captions or graphics, clean audio, sync multicamera footage, add music or voiceover, and export the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brajendrak00068/agentic-ai-video-production/levea-video-editing
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 brajendrak00068/agentic-ai-video-production --skill levea-video-editing
Clone the repo
git clone --depth 1 https://github.com/brajendrak00068/agentic-ai-video-production

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 levea-video-editing

README.md
[![agentmods](https://agentmods.dev/badge/skills/brajendrak00068/agentic-ai-video-production/levea-video-editing/github.svg)](https://agentmods.dev/skills/brajendrak00068/agentic-ai-video-production/levea-video-editing)
Your own site
<a href="https://agentmods.dev/skills/brajendrak00068/agentic-ai-video-production/levea-video-editing"><img src="https://agentmods.dev/badge/skills/brajendrak00068/agentic-ai-video-production/levea-video-editing/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 levea-video-editing

Your own site · 80×15
<a href="https://agentmods.dev/skills/brajendrak00068/agentic-ai-video-production/levea-video-editing"><img src="https://agentmods.dev/badge/skills/brajendrak00068/agentic-ai-video-production/levea-video-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00033 $0.00494
Opus 5.5 $0.00013 $0.00198
Sonnet 5.5 $0.00007 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash 9e4962734d52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

levea-video-editing 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 yesterday.

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.

hermes-plugin/skills/levea-video-editing/SKILL.md · 42 lines

What it actually says

Levea Video Editing

Use the levea_video_edit tool to perform video edits. Send the complete user intent as one natural-language prompt; the Levea backend plans, executes, verifies, repairs, and exports. Do not split one request into many small tool calls.

When to use

  • Trimming, cutting, 9:16 vertical reframing, viral clips from long videos.
  • Captions (caption templates such as hormozi, viral-pop, karaoke, minimal-pro), titles, overlays, motion graphics.
  • B-roll, multicam podcast sync, audio cleanup, music, voiceover, color grading.
  • Exporting the verified timeline to MP4.

Workflow

  1. First call: pass prompt plus video_url (or assets). Save the returned projectId.
  2. Follow-up edits: always pass the same project_id, so edits stack on the committed project.
  3. Read status and success from the result:
    • success: true means the backend verified the edit. Report videoUrl when present.
    • pending with a jobId: call levea_job_status with wait: true to get the rendered file.
    • awaiting_approval: show the plan to the user; resend with workingMemory (and optional editedPlan) to continue.
    • partial or error: tell the user what failed using message; do not claim success.
  4. For very long edits use levea_queue_edit (requires project_id) and poll levea_task_status. If a connection drops mid-edit, levea_active_task reconnects to the running edit for a project.

Example

{
  "prompt": "Cut this podcast into a 30 second 9:16 reel around the strongest hook, add bold animated captions, and export MP4.",
  "video_url": "https://example.com/podcast.mp4"
}
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. yesterday First seen · 42 lines · 33 tokens per session scan A 9e4962734d52

Subscribe to this mod's changes

levea-video-editing is a skill published in the GitHub repository brajendrak00068/agentic-ai-video-production (3 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 494 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-27.

Related

Other skills, from other repositories

kinocut

Use when an agent must edit local video safely. Kinocut guards planning, FFmpeg operations, subtitles, audio, analysis, quality gates, receipts, repurposing, and Hyperframes via MCP, Python, or CLI.

KyaniteLabs/kinocut · 50 tokens

kinocut-repurpose

Use when turning one local video into a platform-ready short. Kinocut builds clip packages with manifests, review artifacts, and human approval gates.

KyaniteLabs/kinocut · 35 tokens

mcp-video

Use when a tool or doc references mcp-video, the former name. Kinocut is the same guarded local video toolkit: inspect, edit, render, verify.

KyaniteLabs/kinocut · 0 tokens

ainb-fleet:daemons

Runtime-health view of the four fleet daemons — phone bridge, notifyd, ATC, and the fleet auto-continue daemon — in one table. Each row reports state (running / stopped / unknown), pid, uptime, last activity, error count, and a HEALTH reason that distinguishes a clean stop from a crash (stale heartbeat) or a…

stevengonsalvez/agents-in-a-box · 126 tokens

ainb-fleet:daemon

Long-running watcher that scans every claude session every 5s and auto-sends continue to any session whose recent tmux pane buffer matches a known API-error regex (ratelimited, overloadederror, internalservererror, requesttimeout, sockethangup, fetchfailed, ECONNRESET). Use this when you want unattended recovery from…

stevengonsalvez/agents-in-a-box · 89 tokens

ainb-fleet:cost

Show fleet spend — per-session, per-model, per-day, and per-group USD cost rollups for every claude/codex session, sourced live from ainb's burndown analytics (which already prices every provider call). Use when you need spend visibility across a multi-session fleet, want to find the most expensive session/model, or…

stevengonsalvez/agents-in-a-box · 120 tokens