agentmods.dev

lc-editor

lc-editor is a skill for Claude Code, Codex from uzairayed/lc-editor. It costs 0 tokens per session (818 once invoked), scanned A, original, MIT.

A video-editing skill for turning raw clips into short 9:16 vertical reels. It uses an lc-editor server to build the timeline and FFmpeg, a video-processing tool, to render the result.

In plain words
What is it for?
It helps import and analyze footage, find and preview strong shots, arrange clips, synchronize edits to music after confirmation, and export a vertical reel.
Why use it?
It gives the agent a defined workflow for selecting footage, deciding what to cut, handling sound, and exporting a reel. It also requires the user's choice between music and natural audio before editing the timeline.

Skill for Claude CodeCodex

0 3d ago A scan 0 tokens original MIT
View the source file uzairayed/lc-editor
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.

agentmods
npx agentmods add skills/uzairayed/lc-editor/lc-editor
Any agent
npx skills add uzairayed/lc-editor --skill lc-editor
Clone the repo
git clone --depth 1 https://github.com/uzairayed/lc-editor

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00818
Opus 5 $0.00000 $0.00409
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 2d ago against content hash 667603983e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lc-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 2d 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/lc-editor/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lc-editor

Use this skill when asked to cut 9:16 vertical reels from raw video clips. The lc-editor MCP server gives you tool calls to build a timeline; ffmpeg does the rendering.

When to use

  • User asks you to edit video clips into a short reel
  • User asks for 9:16 vertical video editing
  • User mentions cutting, trimming, or assembling footage

Quick start

The MCP server is lc-editor. Call its tools to build and export your reel.

Workflow

  1. Analyze footage first. Use import_folder or import_file to bring in media, then media_analyze and shots_list / shots_rank to find the strongest shots. Look at keyframes with thumbnail or contact_sheet before deciding what to cut.

  2. Ask about sound before touching the timeline. Sound is the owner's call, not yours. Ask: "Do you want music or natural audio only?" Do not assume either way.

    • If music: call project_set(allow_music=true), import the track, music_add, beat_analyze, show beat_sync_preview, then beat_sync_apply only after the user confirms.
    • If natural audio: proceed without music tools.

  3. Match subjects to scene cards. When you look at keyframes or set clip durations/roles, consult context/INDEX.md and read only the matching scene cards. The process is in context/HOW.md.

  4. Build the timeline. Use clip_add, trim, split, reorder, motion, and transitions. An occasional two-up is context/scenes/pair.md. A reel that is mostly stacks is context/scenes/collage.md. Two ride POVs is context/scenes/ride-pair.md. Add layers or apply a template if needed.

  5. Run review_report before export. Fix every warning it returns.

  6. Show preview stills at each pass. Use preview_stills so the user can see progress.

Key constraints

  • Canvas: 1080×1920, 30fps
  • Captions: stroke-and-shadow text only, never a box
  • Templates: editorial and karachi (apply expands to ordinary layers)
  • Music is opt-in only via project_set(allow_music=true)
  • Engine rules in specs/craft.md are floors; scene-card judgment can raise them but never lower them

Read the full file on GitHub · 60 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. 2d ago First seen · 60 lines · 0 tokens per session scan A 667603983e26

Subscribe to this mod's changes

lc-editor is a skill published in the GitHub repository uzairayed/lc-editor (0 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 818 tokens. 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.

Creative and media
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens