Measured harness ledgerPublic result
Claude Fable 5.1JRPG boss battle — Claude Fable 5.1 Max
Build an interactive Three.js JRPG boss battle with supplied character assets, required combat beats, animation, sound controls, effects, and a validator-ready game loop.
Max reasoningHeadline result
- Workflow cost
- $108.88
- Wall-clock
- 5h 27m 19s wall-clock
- Processed tokens
- 48.22M processed
- Record state
- partial_token_timing_artifact_validation_ledger_with_independent_replay
Public summary
Claude Fable 5.1 Max partial_token_timing_artifact_validation_ledger_with_independent_replay ledger: 5h 27m 19s wall-clock, 48.22M processed, and $108.88 API-equivalent estimate with 1-hour cache-write pricing, not a subscription invoice.
Run identity and stack
- Result ID: jrpg-boss-battle-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: Supplied GLB fixture bundle
- Stack: Harness v1 JRPG validator
- Stack: Requested tool profile: codex-cli-imagegen
Cost basis
- The full receipt includes two post-generation measurement/correction prompts. The separately reported build segment isolates the frozen JRPG request through its 41/41 validation milestone.
Primary artifact integrity
- Kind: interactive-threejs-jrpg-boss-battle
- Path: artifacts/jrpg-boss-battle-fable-5.1-max/source/src/main.js
- SHA-256: ba9692c80ba9ec8af8a73cce64388522ff326518ad38811391e1ebbe91a30f61
Validation evidence
- Validator SHA-256: b571ff1895fd6a61d98ccb4a9f7ca4ecefc961abfc3f6b77e23742bddd921ab8
Recorded caveats
- The headline full-session wall-clock and cost include post-generation metrics/correction turns and idle gaps; use the separately recorded 43m 29s / $81.38 build segment for that narrower scope.
- Wall-clock is end-to-end workflow latency, not model-only compute.
- Output tokens include hidden reasoning, generated code, visible text, and tool-call JSON.
- Cache reads are discounted, so processed-token totals overstate cost.
- The independent 60.1 FPS validator sample is not a standardized local/RTX performance measurement.
- The validator and smoke test establish functional evidence, not blind visual-quality evaluation.
Visible evidence gaps
- standardized local FPS and RTX Pro 6000 render metadata
- browser and local-hardware identity for the source session
- 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.