scene-review

An interactive command for checking a video project one scene at a time in Remotion Studio, a browser-based workspace for previewing Remotion videos. It is used before creating the voiceover.

In plain words
What is it for?
Use it to review scene timing and appearance, jump to a particular scene, request visual refinements, and approve scenes before voiceover generation.
Why use it?
It gives the user a quality checkpoint while changes are still easy to make. Each scene can be approved, adjusted, refined, flagged, or skipped, with the preview updating as edits are made.

Command for Claude Code

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 commands/digitalsamba/claude-code-video-toolkit/scene-review
Clone the repo
git clone --depth 1 https://github.com/digitalsamba/claude-code-video-toolkit

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,887 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 $0.00014 $0.01887
Opus 5 $0.00007 $0.00944
Sonnet 5 $0.00003 $0.00377
Haiku 4.5 $0.00001 $0.00189

Measured yesterday against content hash 158a373dbabd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scene-review 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/commands/scene-review.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scene Review

Interactive scene-by-scene review using Remotion Studio. Critical quality gate before voiceover generation.

Quick Start

/scene-review           # Review all scenes from beginning
/scene-review title     # Jump to specific scene by type
/scene-review 3         # Jump to scene 3

Example Session

$ /scene-review

Remotion Studio running at http://localhost:3000

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Scene 1 of 6: title (4s, frame 0)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Navigate to frame 0 in Studio and watch the scene.

[1] Approve  [2] Adjust  [3] Refine  [4] Flag  [5] Skip

> 3 (Refine)

Invoking frontend-design skill...
Reading TitleSlide.tsx and adjacent scenes for context...

What aspect needs refinement?
- Color palette feels too flat
- Text animation needs more impact
- Background too static

> Background too static

[Makes changes to TitleSlide.tsx]

Check Remotion Studio - it hot-reloads automatically.
Better? [y/n/more changes]

> y

Scene 1 approved. Moving to Scene 2...

Iterative Feedback Loop

The review follows this cycle for each scene:

┌─────────────┐
│ View scene  │◄──────────────────────┐
│ in Studio   │                       │
└──────┬──────┘                       │
       │                              │
       ▼                              │
┌─────────────┐    ┌─────────────┐    │
│  Evaluate   │───►│   Adjust    │────┤
│             │    │ (config)    │    │
└──────┬──────┘    └─────────────┘    │
       │                              │
       │           ┌─────────────┐    │
       │──────────►│   Refine    │────┘
       │           │ (component) │
       │           └─────────────┘
       ▼
┌─────────────┐
│   Approve   │───► Next scene
└─────────────┘
  • Adjust: Change config values (text, duration, asset paths) → hot-reload → verify
  • Refine: Invoke frontend-design skill for visual improvements → edit component → hot-reload → verify

Repeat until the scene looks right, then approve and move on.

Read the full file on GitHub · 311 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 · 311 lines · 14 tokens per session scan A 158a373dbabd

Subscribe to this mod's changes

scene-review is a command published in the GitHub repository digitalsamba/claude-code-video-toolkit (2,027 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 1,887 once invoked, about $0.0001 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 2026-08-30.