video-editing

video-editing is a skill for Claude Code, Codex from YansIlinta/video-agent-runtime. It costs 60 tokens per session (911 once invoked), scanned A, original, MIT.

A set of structured tools and rules for editing existing videos from their transcripts. It supports reviewing project state, proposing and approving edit plans, diagnosing feedback, adding narration, managing versions, and exporting approved results.

In plain words
What is it for?
It is for turning long videos into shorter edits, finding transcript sections, checking timeline ranges, reviewing visual evidence when needed, and exporting an approved version.
Why use it?
It keeps editing decisions tied to the transcript and project state, reducing accidental changes and unsupported edits. It also requires approval before a new editing direction is applied.

Skill for Claude CodeCodex

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

Good fit It is for turning long videos into shorter edits, finding transcript sections, checking timeline ranges, reviewing visual evidence when needed, and exporting an approved version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yansilinta/video-agent-runtime/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 YansIlinta/video-agent-runtime --skill video-editing
Clone the repo
git clone --depth 1 https://github.com/YansIlinta/video-agent-runtime

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 video-editing

README.md
[![agentmods](https://agentmods.dev/badge/skills/yansilinta/video-agent-runtime/video-editing.svg)](https://agentmods.dev/skills/yansilinta/video-agent-runtime/video-editing)
Your own site
<a href="https://agentmods.dev/skills/yansilinta/video-agent-runtime/video-editing"><img src="https://agentmods.dev/badge/skills/yansilinta/video-agent-runtime/video-editing.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 911 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 $0.00060 $0.00911
Opus 5 $0.00030 $0.00456
Sonnet 5 $0.00012 $0.00182
Haiku 4.5 $0.00006 $0.00091

Measured 7d ago against content hash 1c6e9af71b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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.

skills/video-editing/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video editing runtime

Use the runtime as the project authority. Do not edit its JSON files, construct FFmpeg commands, or bypass validation.

Start with state and evidence

  1. Call project_status.
  2. Call system_status before choosing a real provider path; unavailable optional alignment or TTS is not permission to pretend it ran.
  3. Read the active transcript, transcript_quality, and timeline before proposing changes. Prefer transcript_search, transcript_inspect_range, and timeline_inspect_range over re-reading large artifacts.
  4. Call visual_inspect_range only when the decision genuinely needs visual evidence. Do not inspect every frame or send the whole video to a vision model by default.
  5. Surface low-confidence words, failed alignment, speaker overlap, or other transcript-quality warnings when they affect an editing decision.

Approval-gated edit loop

For a new edit direction:

  1. Understand the requested outcome and constraints.
  2. Call strategy_propose and explain its structure, target duration, selection policy, pace, captions, and rationale.
  3. Wait for explicit user approval. Then call strategy_approve.
  4. Call edit_plan_create, edit_plan_validate, and edit_plan_diff in that order.
  5. If validation fails, fix the structured plan; never work around it in the renderer.
  6. Show the meaningful diff and apply only after it is consistent with the approved strategy.
  7. Call edit_plan_apply, then preview_render.
  8. Review the self-check result and ask the user to assess the preview.
  9. Call final_approve and export_video only after explicit final approval.

Never treat self-evaluation as user approval.

Feedback and replanning

  • Submit the user's original words with feedback_submit; include category and range when known.
  • For a local complaint such as “20–35 seconds is slow,” prefer the smallest plan change affecting that range. Preserve unrelated clips.
  • Call workflow_diagnose before repeated retries.
  • Use PATCH for a localized execution problem. Use REPLAN when feedback indicates the EditingStrategy is wrong.
  • For PATCH, call edit_patch_plan, edit_patch_validate, and edit_patch_diff; reject out-of-scope/global mutations before edit_patch_apply.
  • When diagnosis returns REPLAN, call workflow_replan, present the replacement strategy, and wait for a fresh approval.
  • Repeated “flat,” “not interesting,” or “weak opening” feedback is evidence of a possible story-structure mismatch, not permission to randomly move cuts again.
  • Explain what changed, why it changed, and which feedback caused it. Use version comparison when that is clearer.

Read the full file on GitHub · 62 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. 7d ago First seen · 62 lines · 60 tokens per session scan A 1c6e9af71b24

Subscribe to this mod's changes

video-editing is a skill published in the GitHub repository YansIlinta/video-agent-runtime (1 stars, last pushed 13d ago), licensed MIT. It adds 60 tokens to every session and 911 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

vidgrid

Give an AI agent eyes for video. Turn a local video file (MP4, MOV, WebM) into a numbered grid of frames plus a transcript that a vision model can read — so you can summarize a talk, find the exact moment something happens, read on-screen text or UI, or rank clips. Use whenever you need to watch, analyze, or…

pawvej/vidgrid · 85 tokens

claude-real-video

Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.

HUANGCHIHHUNGLeo/claude-real-video · 61 tokens

edit-video

Edit video with FableCut — assemble a cut, add titles and captions, grade, add transitions, keyframe animation, speed ramps, and export. Use whenever the user wants to cut, trim, caption, subtitle, grade, or otherwise edit a video, or asks to open/start the video editor.

ronak-create/FableCut · 62 tokens

remake-reel

Analyze a reference video (a reel, montage, or ad the user likes) into an edit blueprint — shot boundaries, music beats, BPM, energy curve, the drop — and rebuild the same structure with the user's own footage. Use when someone says "make it like this video", "remake this reel with my clips", or asks what makes an…

ronak-create/FableCut · 74 tokens

claude-real-video-for-agents

Install and use crv (claude-real-video) — a tool that lets any AI agent watch videos by extracting scene-aware keyframes, deduplicating them, and transcribing audio. Use when the user shares a video URL or file and wants it analyzed, summarized, or discussed.

HUANGCHIHHUNGLeo/claude-real-video · 66 tokens

authoring-video-templates

Use when creating or editing a video template JSON (the template descriptor), adding or changing sections/filters/maps/variables/transitions/looks/motion/audio/layers, or debugging template validation errors in ffmpeg-video-composer.

heristop/leclap · 51 tokens