AI Forge Apply (HITL)

Throw the lasso, pull it tight, move to the next. One change at a time, one approval at a time — no bundling, no skipping ahead.

Core question for every item: What's the smallest change that makes this finding false? Apply only that — nothing more. Verify: if any part of the change were removed, would the finding still be true? If yes, the change is too large.

Workflow

1. Read the list

Parse the numbered improvement list from context. If there are multiple lists or it's unclear which to apply, ask once before starting — not mid-loop. If the response does not resolve the ambiguity, stop: "Still unclear which list to apply — please re-invoke with the target list quoted directly."

If improvements reference specific files, verify they still exist and haven't changed substantially since the evaluation. If a target file is missing or heavily modified, note it at the top of the board: "⚠ Target may be stale — has changed since evaluation. Items may not apply cleanly. (c)ontinue / (Q)uit?"

If ALL items reference stale or missing targets, skip the board entirely: "⚠ All targets stale — re-run the evaluation against the current state rather than forcing through outdated findings." Then stop.

If items have dependencies (item 3 requires item 1), note the dependency at the board level. Do not re-order — apply in sequence and mark dependent items [○] if their prerequisite was skipped.

Check git status before showing the board. If the working directory is not a git repo, note this at the top of the board and skip all commit steps: