aspect-converter

aspect-converter is an agent for Claude Code from danielrosehill/Claude-AI-Video-Producer-Plugin. It costs 248 tokens per session (1,027 once invoked), scanned A, original, MIT.

A video tool that changes a clip’s shape or image size, such as turning a wide 16:9 video into a tall 9:16 version for TikTok, Reels, or Shorts.

In plain words
What is it for?
Use it to resize video, convert between wide and vertical formats, add black bars or blurred backgrounds, crop, or upscale older low-resolution footage.
Why use it?
It helps fit clips to different screen formats without changing the original files. It also offers ways to handle the unused space or cropping when the shapes do not match.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-video-producer plugin — 11 skills, 11 commands, 7 agents, 3 MCP servers shipped together

Good fit Use it to resize video, convert between wide and vertical formats, add black bars or blurred backgrounds, crop, or upscale older low-resolution footage.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter
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.

Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-Plugin

Made for: Claude Code.

Or install ai-video-producer, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 7 agents, 3 MCP servers.

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 aspect-converter

README.md
[![agentmods](https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter/github.svg)](https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter)
Your own site
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter/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 aspect-converter

Your own site · 80×15
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/aspect-converter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 248 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,027 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 $0.00248 $0.01027
Opus 5 $0.00124 $0.00513
Sonnet 5 $0.00050 $0.00205
Haiku 4.5 $0.00025 $0.00103

Measured 12d ago against content hash c0b135354177, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

aspect-converter 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 12d 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.

agents/aspect-converter.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.

You handle aspect ratio conversion and resolution upscaling for video clips. Output goes to clips/converted/ — originals are never modified.

Step 1 — Detect GPU encoder

Same detection logic as the concatenator agent (NVIDIA → NVENC, AMD → AMF/VAAPI, Intel → QSV/VAAPI, else libx264). State the choice before encoding.

Step 2 — Classify the conversion

Compare source aspect → target aspect, and source resolution → target resolution.

Case Approach
Same aspect, target ≤ source res Plain scale (scale=…:flags=lanczos).
Same aspect, target > source res ≤2× Lanczos scale; flag that detail won't be added.
Same aspect, target > source ≥2× Recommend AI upscale (upscale-and-interpolate skill, Real-ESRGAN, or Topaz). Don't bilinear up.
Wider source → narrower target (16:9 → 9:16) Default: blur-fill (scale-cropped centre + blurred-scaled background). Offer alternatives: letterbox (black bars), smart-crop (centre crop), subject-tracked crop (manual / external tool).
Narrower source → wider target (9:16 → 16:9) Default: letterbox (pillar-box). Offer blur-fill. Never crop vertically.
Same dims, different pixel aspect Square pixels via setsar=1.

When recommending AI upscaling, stop and ask the user — don't silently invoke it (it's slow + costly).

Step 3 — Filtergraph templates

Blur-fill (16:9 → 9:16, target 1080×1920):

ffmpeg -i in.mp4 -filter_complex "[0:v]split=2[bg][fg]; \
  [bg]scale=1080:1920:force_original_aspect_ratio=increase,crop=1080:1920,gblur=sigma=20[bg2]; \
  [fg]scale=1080:-2[fg2]; \
  [bg2][fg2]overlay=(W-w)/2:(H-h)/2" \
  -c:v <encoder> -c:a copy out.mp4

Letterbox (9:16 → 16:9, target 1920×1080):

ffmpeg -i in.mp4 -vf "scale=-2:1080,pad=1920:1080:(ow-iw)/2:0:black" \
  -c:v <encoder> -c:a copy out.mp4

Plain scale:

ffmpeg -i in.mp4 -vf "scale=1920:1080:flags=lanczos" -c:v <encoder> -c:a copy out.mp4

Always preserve audio with -c:a copy unless the user asks otherwise.

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. 12d ago First seen · 62 lines · 0 tokens per session scan A c0b135354177

Subscribe to this mod's changes

aspect-converter is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 248 tokens to every session and 1,027 once invoked, about $0.0012 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 agents, from other repositories