From claude-meta-tools
Verify no behavioral regressions after implementation. Spawns parallel sonnet subagents for semantic diff review + test execution. Use when: user says "verify no regressions", "check for regressions", "make sure nothing broke".
npx claudepluginhub bengous/claude-code-plugins --plugin claude-meta-toolsThis skill uses the workspace's default tool permissions.
Usage: `/verify-no-regressions [count] [base-branch]` (defaults: 1 main)
Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.
Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.
Writes implementation plans from specs for multi-step tasks, mapping files and breaking into TDD bite-sized steps before coding.
Share bugs, ideas, or general feedback.
Usage: /verify-no-regressions [count] [base-branch] (defaults: 1 main)
git status --short 2>/dev/null || echo "(not a git repo)"set -- $ARGUMENTS; git log --oneline "${2:-main}"...HEAD 2>/dev/null || echo "(none or invalid base)"set -- $ARGUMENTS; git diff --stat "${2:-main}"...HEAD 2>/dev/nullgit diff --cached --stat 2>/dev/nullgit diff --stat 2>/dev/nullcat package.json 2>/dev/null | jq -r '.scripts | to_entries[] | select(.key | test("test";"i")) | "\(.key): \(.value)"' 2>/dev/null || echo "(no package.json)"Read the work state above to determine what happened:
git diff base...HEADgit diff --cachedIf nothing changed anywhere, report that and stop.
Spawn sonnet subagents in a single message. Tell each agent which diff commands to use based on the work state.
Semantic reviewers -- split changed files across $0 agent(s) (default: 1). Each agent:
Test runner (skip if no test infrastructure) -- one additional agent that runs the test suite and reports PASS / FAIL.
After all agents complete, synthesize a single report with overall verdict.