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".
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-meta-tools:verify-no-regressionsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Usage: `/verify-no-regressions [count] [base-branch]` (defaults: 1 main)
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.
npx claudepluginhub bengous/claude-code-plugins --plugin claude-meta-toolsVerifies recent code changes don't break existing functionality by analyzing Git diffs, dependencies, running affected tests (unit/integration/e2e), and integration checks.
Validates code changes against original plan using git diffs and full file reads, then launches parallel subagents for quality, security, and test coverage checks. Use post-implementation or /recheck.
Reads a git diff and generates a prioritized browser-QA plan of user-facing workflows affected by the change, optionally recording them as a session with a report.