code-review-fix

Arguments:

• Phase number (required) — which phase's REVIEW.md to fix (e.g., "2" or "02")
• --all (optional) — include Info findings in fix scope (default: Critical + Warning only)
• --auto (optional) — enable fix + re-review iteration loop, capped at 3 iterations

Output: {padded_phase}-REVIEW-FIX.md in phase directory + inline summary of fixes applied

<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/code-review-fix.md </execution_context>

Optional flags parsed from $ARGUMENTS:

• --all — Include Info findings in fix scope. Default behavior fixes Critical + Warning only.
• --auto — Enable fix + re-review iteration loop. After applying fixes, re-run code-review at same depth. If new issues found, iterate. Cap at 3 iterations total. Without this flag, single fix pass only.

Context files (CLAUDE.md, REVIEW.md, phase state) are resolved inside the workflow via bm-sdk query init.phase-op and delegated to agent via config blocks.

Execute the code-review-fix workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/code-review-fix.md end-to-end.

The workflow (not this command) enforces these gates:

• Phase validation (before config gate)
• Config gate check (workflow.code_review)
• REVIEW.md existence check (error if missing)
• REVIEW.md status check (skip if clean/skipped)
• Agent spawning (gsd-code-fixer)
• Iteration loop (if --auto, capped at 3 iterations)
• Result presentation (inline summary + next steps)