| { | |
| "method": "One fresh Claude Code subagent per task x config, same model, no file outputs. Metrics from task telemetry: total tokens (includes thinking), duration. Code lines counted from fenced blocks in the deliverable.", | |
| "configs": [ | |
| "baseline — no skill", | |
| "caveman — caveman SKILL.md (full) as operating instructions", | |
| "ponytail — ponytail SKILL.md (full) as operating instructions" | |
| ], | |
| "tasks": [ | |
| { "id": "email", "prompt": "Write me a Python function that validates email addresses." }, | |
| { "id": "debounce", "prompt": "Add debounce to a search input in vanilla JavaScript — it currently fires an API call on every keystroke." }, | |
| { "id": "csv-sum", "prompt": "Write Python code that reads sales.csv and sums the 'amount' column." }, | |
| { "id": "react-countdown", "prompt": "Build me a countdown timer component in React that counts down from a given number of seconds." }, | |
| { "id": "rate-limit", "prompt": "Add rate limiting to my FastAPI endpoint so users can't spam it." } | |
| ] | |
| } | |