jbarbier

Estimates what a codebase would have cost to build with a traditional human team — the replacement cost to rebuild, not market value. Use when the user asks "how much did this cost?", "what's the ROI of Claude/Copilot on this repo?", "how long would a human team have taken?", or mentions COCOMO, LOCOMO, Function Points, LOC analysis, or codebase cost. Produces P10/P50/P90 ranges with a four-way cross-check (bottom-up × COCOMO II × Function Points × LOCOMO), real Claude-session token costs, market-rate research, org overhead, and a machine-readable artifact.