Claude Opus 5.5 in Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills)
skills off
The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).
Wall time 52m 44sCost $4.65 reported
Review
No verdict yet.
The full review
Stopped by us. Stopped by us (isolated box lifetime (60 min) reached; infra stop, not a harness result); not a model failure.
Scores
Not scored: only runs that finished on their own are scored.
Downloads
Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.
The exact prompt
as run, 721 characters. Every result for this prompt
ok here it is - my first Opus 5.5 vibecoded threejs 3D experience my God!! Opus is creative!! I made a road that forgets which way is down. It folds 90° up a yellow wall, runs upside down across a ceiling, and turns into sheet music: steer through the notes to play each street's melody. Watercolour. Ink. A radio on the roof. #vibejam Build it as index.html (plus any local asset files you create) in the current directory. Three.js may load from a pinned CDN. You may serve it locally and open it in headless chromium (/usr/bin/chromium, software WebGL, no GPU) to screenshot and inspect your own output, and iterate on your own before finishing. Close any browser you open as soon as you've taken your screenshot.
How it was made
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 machine-format transcript is published as a scrubbed download.
Show all 2 steps
Loading the timeline…
Download the full transcript transcript, 508 KB. 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 $4.65, as reported by Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) (its own bill for the run). The list-price estimate from the token counts is $4.65.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 32 | $4.00 | $0.0001 |
| Cache write | 195,623 | $5.00 | $0.9781 |
| Cache read | 1,468,546 | $0.20 | $0.2937 |
| Output | 169,030 | $20.00 | $3.3806 |
| of which reasoning | not recorded | billed as output |
- Total computed from tokens
- $4.6526
- Total reported by the harness
- $4.6526
- Difference
- matches
Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) reported its own total; token counts x list prices shown beside it. usage from the harness's own JSON events (message_end usage; cost.total as reported)
Prices: Project price table (vendor list prices), 2026-09-22.
Run notes
- frozen prompt (reconstructed): recovery/prompts_recovered/folding_road_threejs.assembled_candidate.txt: verbatim ask + recorded harness suffix
- Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills): headless one-shot mode (TUI not automatable), run in tmux for screenshots
- Mode: headless mode (TUI not automatable) — pi --mode json in tmux, inside bubblewrap
- Isolation audit: outside paths seen