reelforge: Skill for Claude Code

.claude/skills/reel/SKILL.md

reel is a skill for Claude Code from waseemnasir2k26/reelforge. It costs 84 tokens per session (526 once invoked), scanned A, original, MIT.

A video-editing workflow that turns one raw talking-head clip into a vertical 9:16 social-media video with on-screen captions and an opening hook card.

In plain words
What is it for?
Use it to make publishable reels from raw video. It transcribes speech locally, burns word-synced captions into the video, shows a hook card for the first 2.5 seconds, and exports at 1080×1920.
Why use it?
It removes the need to transcribe, crop, caption, and export the clip manually.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is waseemnasir2k26/reelforge's own configuration. It tells Claude Code how to work on reelforge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything reelforge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to waseemnasir2k26/reelforge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/waseemnasir2k26/reelforge/main/.claude/skills/reel/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/waseemnasir2k26/reelforge

Made for: Claude Code.

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 reel

README.md
[![agentmods](https://agentmods.dev/badge/skills/waseemnasir2k26/reelforge/reel/github.svg)](https://agentmods.dev/skills/waseemnasir2k26/reelforge/reel)
Your own site
<a href="https://agentmods.dev/skills/waseemnasir2k26/reelforge/reel"><img src="https://agentmods.dev/badge/skills/waseemnasir2k26/reelforge/reel/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 reel

Your own site · 80×15
<a href="https://agentmods.dev/skills/waseemnasir2k26/reelforge/reel"><img src="https://agentmods.dev/badge/skills/waseemnasir2k26/reelforge/reel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 526 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 $0.00084 $0.00526
Opus 5 $0.00042 $0.00263
Sonnet 5 $0.00017 $0.00105
Haiku 4.5 $0.00008 $0.00053

Measured 11d ago against content hash 469562be01bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

reel 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 11d 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.

.claude/skills/reel/SKILL.md · 52 lines

What it actually says

AI Auto-Edit Reel Pipeline (SkynetLabs)

You turn ONE raw take into a publish-ready reel. No timeline, no human editor.

When to use

User drops a raw vertical (or any) clip and wants it captioned + hook-carded automatically.

Steps

  1. Deps: ensure ffmpeg is on PATH. Ensure faster-whisper installed (pip install -r requirements.txt if not).
  2. Run:
    python auto_reel.py "<clip>" --hook "<HOOK TEXT>" --sub "<SUBLINE>" --out reel.mp4
    
  3. Verify: ffprobe the output → confirm 1080x1920 and sane duration.
  4. Report the path and offer next step (schedule / caption pack).

What the script does

  • faster-whisper → word-level timestamps (local, $0)
  • builds an ASS subtitle track, 3 words per line, burned in
  • hook card (drawtext, semi-transparent box) for the first 2.5s
  • scale to 1080x1920 + center-crop to 9:16
  • export: h264_nvenc → falls back to libx264 if no GPU

Flags

  • --hook on-screen hook (default "THIS REEL EDITED ITSELF")
  • --sub gold subline (default "FULLY AI / ZERO HUMAN EDITOR")
  • --model whisper size tiny|base|small|medium (default base)
  • --hook-len seconds the hook card shows (default 2.5)
  • --wpl words per caption line (default 3)

Gotchas

  • Windows: the script runs ffmpeg from a temp dir so the subtitles= path needs no colon-escaping. Don't "fix" it to an absolute path.
  • No audio in clip → script exits early; that's correct.

Built by SkynetLabs — www.skynetjoe.com

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. 11d ago First seen · 52 lines · 84 tokens per session scan A 469562be01bb

Subscribe to this mod's changes

reel is a skill published in the GitHub repository waseemnasir2k26/reelforge (6 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 526 once invoked, about $0.0004 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

atmos-cast

Atmos cast recording and rendering: atmos cast play/render, output-format inference (gif/mp4/html/ascii/png/jpg/jpeg), the --cast/ATMOSCAST auto-recording flag, workflow type: cast (steps/session modes) and type: simulate step types, and committed .cast screengrabs.

cloudposse/atmos · 66 tokens

cli-anything-photoshop

A command-line tool that controls Adobe Photoshop through Windows automation. It can work with Photoshop documents, layers, selections, text, image adjustments, and exports.

yb2460/harness-anything · 43 tokens

youtube

Use whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation. Manages videos, playlists, comments, captions, subscriptions, thumbnails, analytics, and more.

eat-pray-ai/yutu · 48 tokens

verticals

AI-native vertical video engine with niche intelligence. Takes a one-line topic and a niche profile, and outputs a finished YouTube Short/Reel/TikTok with AI-generated b-roll, voiceover, burned-in captions, background music, and thumbnail. Supports multiple LLM providers (Claude, Gemini, GPT, Ollama), TTS providers…

rushindrasinha/youtube-shorts-pipeline · 93 tokens

rexai-image-generation

An image-generation skill that uses RexAI to create new images from text or transform existing images from other images. It returns the result as a local file.

rexleimo/aios · 80 tokens

brainstorming

A structured idea-generation and selection workflow. It uses methods such as SCAMPER, “How Might We” questions, Crazy 8s, ICE scoring, and voting to move from many ideas to a short list.

Insajin/autopus-adk · 16 tokens