Measured harness ledgerPublic result
Claude Fable 5.1Explorable space-flight game — Claude Fable 5.1 Max
Build a responsive browser space-flight game with flight controls, a coherent star-system environment, lighting, assets, and a playable game loop.
Max reasoningHeadline result
- Workflow cost
- $129.75
- Wall-clock
- 1h 12m 48.2s wall-clock
- Processed tokens
- 65.60M processed
- Record state
- partial_token_timing_artifact_build_and_independent_browser_input_replay_ledger
Public summary
Claude Fable 5.1 Max partial_token_timing_artifact_build_and_independent_browser_input_replay_ledger ledger: 1h 12m 48.2s wall-clock, 65.60M processed, and $129.75 Official Anthropic API-list-price equivalent, not an itemized Claude Code subscription charge..
Run identity and stack
- Result ID: space-flight-game-threejs-fable-5.1-max
- Technical model: claude-fable-5.1
- Provider: Anthropic Claude Code
- Stack: Anthropic Claude Code
- Stack: Technical model/configuration: claude-fable-5.1
- Stack: Three.js / Vite game
- Stack: Generated spaceship assets
- Stack: Harness v1 space-flight prompt
Cost basis
- All-5-minute cache-write alternative: $113.21.
Primary artifact integrity
- Kind: manifest-verified-artifact
- Path: artifacts/space-flight-game-threejs-fable-5.1-max/source/src/main.js
- SHA-256: 1774a4458c78489abef72d129cb5000ee7c1a2aadad31de0cb610e83b0106711
Recorded caveats
- Wall-clock is end-to-end workflow latency, including tool execution and waits; it is not model-only compute time.
- Output tokens include hidden reasoning, generated code, and tool-call JSON.
- Cache-read tokens are discounted, so total processed tokens materially overstate effective cost.
- The supplied receipt declares one-hour cache writes; the primary cost follows that declaration and retains an all-five-minute sensitivity.
- The clean source build passed. The bundled candidate gameplay script is not clean-install runnable because playwright-core is undeclared; an independent isolated-dependency replay of the archived source passed the documented input smoke checks.
- No standardized FPS/hardware receipt or blind visual-evaluation record is available.
Visible evidence gaps
- candidate prompt-delivery and one-shot protocol receipt
- standardized FPS, browser, viewport, and hardware receipt
- multi-minute gameplay soak and collision-route receipt
- blind-evaluation record
Public result only
This result keeps its public summary and evidence, but it does not currently have a matching Builder test with prompts, projects, Harness workflows or skills.