From GSD Core
Runs an audit, classifies findings as auto-fixable or manual-only, then autonomously fixes, tests, and commits auto-fixable issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gsd-core:gsd-audit-fix --source <audit-uat> [--severity <medium|high|all>] [--max N] [--dry-run]--source <audit-uat> [--severity <medium|high|all>] [--max N] [--dry-run]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<objective>
Flags:
--max N — maximum findings to fix (default: 5)--severity high|medium|all — minimum severity to process (default: medium)--dry-run — classify findings without fixing (shows classification table)--source <audit> — which audit to run (default: audit-uat)
<execution_context> @~/.claude/gsd-core/workflows/audit-fix.md </execution_context>
Execute end-to-end.npx claudepluginhub open-gsd/gsd-coreAutomates a multi-round audit-fix-verify cycle: Claude audits code, Codex applies fixes, Claude verifies. Repeats up to 3 rounds until all issues resolved. Useful after writing features or before commits.
Verifies fix commits properly address security audit findings without introducing new bugs or regressions.
Audits the full codebase for security, quality, and reliability issues, creates GitHub issues for each finding, then fixes them in isolated git worktrees and submits PRs.