AI Model Reviewer

GPT-6 Sol in Codex CLI 0.156.1 + Remotion/HyperFrames skills

skills on · Codex CLI 0.156.1 + Remotion/HyperFrames skillsKit: remotion 4.0.532 · 4 of 12 installed skills used in the session

← Open in the gallerySame prompt, all models

Rendered video (by the agent)

Poster for rendered video (by the agent)

Rendered video (by the agent). This is the finished MP4 saved in the run. Played from a 720p web copy made by this site from the agent's out.mp4; the original file is too large for this host and is kept unchanged on the runs branch. Download video (2.8 MB).

OKOrbital launch sequencemax effortNeutral harness

Wall time 13m 16sCost $1.71 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 13.3 min.

Scores

AI judge

Not scored

No rubric for this prompt

Visitor votes and reviewer grades are not available yet.

AI judge
AI judge: the test runner (model claude-opus-5-5), scoring by visual review of the 1600 px render against the pre-registered rubric. No AI-judge score exists for this result: there is no rubric for this prompt, so no score is shown and none is made up.
Visitors
Public voting with a blind reveal is coming: you score the output first, then see the other scores.
Reviewer
The reviewer's own grade appears here once it is added.

Scores compare results for the same prompt only. AI-judge boards rank runs within one prompt, equal totals sharing a rank; scores from different prompts are never averaged.

Downloads

Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.

The exact prompt

as run, 3,557 characters. Every result for this prompt

[Task]
Create a 30-second cinematic motion-graphics video, 1920x1080 at 30 fps, of an original rocket, the Kestrel IV, launching from a coastal pad and reaching orbit under a live telemetry HUD.

[Scenes]
1. 0-5 s: Dusk over a coastal launch pad. A slow push-in from a wide shot. Cryogenic vapour curls off the rocket's frosted first stage. Three gantry arms retract one after another. A small mono label reads 'PAD 39-K / T-00:00:10'.
2. 5-9 s: Countdown. Giant numerals 5, 4, 3, 2, 1 slam in one per 0.8 s. Each digit splits horizontally and slides apart to reveal the next. Camera shake builds frame by frame. At 9 s the word IGNITION flashes in white.
3. 9-15 s: Liftoff. The engine bell blooms with light and a particle plume pours sideways into billowing exhaust clouds. The camera tilts up to track the climb. The HUD assembles itself from corner brackets: T+ clock, altitude, velocity, downrange distance and a throttle bar.
4. 15-20 s: Climb through Max-Q. The sky grades from orange to deep indigo and the first stars appear. Shock diamonds pulse in the exhaust. A MAX-Q callout pops in, and a small graph traces the ascent curve live.
5. 20-25 s: Stage separation. The camera arcs to a side profile. A pyro ring flashes, the spent first stage tumbles away and two interstage panels spin off. The second stage lights with a thin blue flame. HUD: STAGE SEP CONFIRMED.
6. 25-30 s: Orbit insertion. The camera pulls far back to reveal the planet's curved limb and a thin atmosphere glow. A dotted orbit ellipse draws itself and the rocket icon settles onto it. HUD reads ORBIT NOMINAL 412 x 418 km, then resolves into the title card KESTREL IV / MISSION 07.

[Style]
Palette: #0B1026 night, #FF7A3D flame, #FFD9A0 glow, #5FE1FF HUD cyan, #F2F4F8 white. The HUD uses a condensed technical sans with tabular digits. The countdown uses a heavy display sans. Add volumetric glow, soft film grain and atmospheric haze. Moves ease with expo-out. HUD panels arrive with springy overshoot and a 60 ms stagger.

[Wow]
- The exhaust is a seeded particle system of at least 2,000 particles, with heat-coloured lifetimes and smoke that expands and drifts.
- Parallax depth: clouds, sea, pad and sky move at distinct rates during the tilt-up.
- The countdown digits cast light onto the scene, and the rocket body is rim-lit by the flame.
- Telemetry values tick continuously and follow physically plausible curves.
- The camera move is continuous from pad to orbit, with no static frames.

[Rules]
- Every frame is drawn in code (SVG, canvas, CSS or WebGL). No image files, no image generation, no external assets beyond fonts.
- Deterministic: no unseeded randomness at render time.
- Text must be crisp, spelled correctly and readable at 1080p.
- No hard cuts between scenes: every change is a designed transition.
- Altitude and velocity only increase after liftoff, and they stay consistent with the T+ clock.

[Harness notes] Render the final video to out.mp4 (1920x1080, 30 s). Write everything into the working directory. Remotion 4.0.527 is already installed for you in the current directory: node_modules is pre-installed and read-only, so do not run npm install or create-video, and a remotion.config.ts here already points rendering at the local Chromium. Render the final video yourself to out.mp4 in the current directory (for example npx remotion render <entry file> <composition id> out.mp4). You may render stills or frames and inspect your own output (headless chromium is available at /usr/bin/chromium) and iterate on your own before finishing.

How it was made

Wall time 13m 16sFirst artifact at 12m 17s2 saved versions

Versions saved during the run

2 intermediate outputs, in the order the model wrote them.

Version 2 of 2
  1. Version 1 at 12m 20s thumbnailv1 12:20
  2. Version 2 at 13m 02s thumbnailv2 13:02

Step by step

The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full transcript is 21.3 MB; it is published as a scrubbed, compressed download rather than shown on the page.

Show all 109 steps

Loading the timeline…

Download the full transcript Codex CLI rollout JSONL, 123 KB, gzip. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.

Cost breakdown

Headline cost $1.71, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)150$2.00$0.0003
Cache write121,800$2.00$0.2436
Cache read3,919,265$0.20$0.7839
Output67,832$10.00$0.6783
of which reasoning34,036billed as output
Total computed from tokens
$1.7061
Total reported by the harness
none

Computed from harness-reported token counts x list prices. Cache writes priced at the input rate (the price table has no separate cache-write price). No request above 272,000 input tokens (50 checked): standard rates.

Prices: Project price table, 2026-09-25.

Run notes

one prompt, agentic harness (self-review allowed)

  • frozen prompt (written): written 2026-10-03 for MR wave rh (owner ask m:d1f2d829 + m:1122fe24: more Remotion and HyperFrames, ambitious multi-scene, harness runs); concept 'orbital_launch_sequence' (shared by the Remotion and HyperFrames tests); all frames code-drawn; standard remotion harness suffix (30 s); zero results
  • plain CODEX_HOME copy (config.toml and framework skills, run work/ trusted; no AGENTS.md/state)
  • W2 remotion skills installed in this run's codex_home/skills
  • W2: the framework's pinned node_modules is bound read-only at work/node_modules (the prompt's 'pre-installed and read-only'); Node 22.23.3 and work/node_modules/.bin first on PATH; headless Chromium /usr/bin/chromium
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Isolation audit: outside paths seen