agentmods.dev

levea-video-editor

levea-video-editor is a skill for Claude Code from brajendrak00068/agentic-ai-video-production. It costs 71 tokens per session (579 once invoked), scanned A, original, MIT.

A natural-language video editing service that turns an editing brief and source video into an exported MP4 file. It can make clips, captions, vertical reframes, motion graphics, music, multicamera edits, and other listed changes through Levea’s hosted tools.

In plain words
What is it for?
Use it to cut videos, add word-by-word captions or subtitles, remove silences, create short vertical versions, add B-roll or graphics, edit multicamera podcasts, adjust colour, and export an MP4.
Why use it?
It removes the need to describe every editing operation as separate tool calls. You can give one brief, while the service plans the edit and checks the rendered result.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the levea-video-editor plugin — 1 skill shipped together

not rated 4repo yesterday A scan 71 tokens original MIT

Good fit Use it to cut videos, add word-by-word captions or subtitles, remove silences, create short vertical versions, add B-roll or graphics, edit multicamera podcasts, adjust colour, and export an MP4.

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

Made for: Claude Code.

Or install levea-video-editor, the plugin that ships this one along with the rest of its 1 skill.

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-editor

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/brajendrak00068/agentic-ai-video-production/levea-video-editor"><img src="https://agentmods.dev/badge/skills/brajendrak00068/agentic-ai-video-production/levea-video-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 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 $0.00071 $0.00579
Opus 5.5 $0.00028 $0.00232
Sonnet 5.5 $0.00014 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured yesterday against content hash ef152f8b1870, 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-editor 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.

claude-plugin/skills/levea-video-editor/SKILL.md · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Levea video editing

Levea is a hosted video editor that is itself an agent: send the user's brief to autonomous_edit and it plans, edits, checks the result on the rendered frames, and exports an MP4. The tools come from the levea MCP server bundled with this plugin; on first use, run /mcp, select levea, and sign in.

Workflow

  1. Get the source. Edits need a public video URL (direct MP4, Google Drive, Dropbox, YouTube) passed as video_url or assets. For a local file, call asset_upload_url, upload the file to the returned URL, and pass the resulting asset URL.
  2. Send the brief verbatim to autonomous_edit as prompt. Do not split one request into several calls; the editor plans multi-step edits itself.
  3. Keep the project_id from the response and pass it on every follow-up edit of the same video.
  4. Long edits. A full edit with motion graphics, music, and export can take 10-20 minutes. Prefer queue_edit (returns a taskId, then poll check_task_status) for those. If autonomous_edit returns status: "running", the edit is still going: call get_active_task with the project_id; never start the edit again.
  5. Plan approval. For destructive or costly work set requirePlanApproval: true. On status: "awaiting_approval", show the plan; when the user agrees, call again with the returned workingMemory and planDecision: "approve".
  6. Report honestly. Give the user videoUrl. Read verificationReport.status: only verified means the result passed its checks; otherwise say what verificationReport and qualityNotes report.

Tips

  • Name caption looks in the prompt ("Hormozi-style", "karaoke", "Spotlight") or pass captionTemplatePreset; list_caption_templates lists exact ids.
  • Brand kits (list_brand_kits, create_brand_kit) carry colors, fonts, logo, and grading; pass brandId.
  • Read-only questions about a video ("what does the transcript say?") go to autonomous_edit too and don't trigger an export.

Read the full file on GitHub · 24 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. yesterday First seen · 24 lines · 71 tokens per session scan A ef152f8b1870

Subscribe to this mod's changes

levea-video-editor is a skill published in the GitHub repository brajendrak00068/agentic-ai-video-production (4 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 579 once invoked, about $0.0003 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 2026-11-05.

Creative and mediaai-agentsclaudeclinecursormcpmcp-server
Related

levea-video-editor compared with skills from other repositories

levea-video-editor next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
levea-video-editorbrajendrak00068/agentic-ai-video-productionSkill4yesterdayMITA71Claude Code
requirements-authoringgriddynamics/rosettaSkill373todayApache-2.0A0Claude Code
specflow-usegriddynamics/rosettaSkill373todayApache-2.0A27Claude Code
memorix-troubleshootingAVIDS2/memorixSkill9152d agoApache-2.0A36Claude Code
solr-schemagriddynamics/rosettaSkill373todayApache-2.0A25Claude Code, Codex
hitlgriddynamics/rosettaSkill373todayApache-2.0A168Claude Code
reasoninggriddynamics/rosettaSkill373todayApache-2.0A34Claude Code