From dev
You are performing a post-implementation quality check on the current diff. The user has already made changes and wants them reviewed, documented, and prepared for commit.
How this command is triggered — by the user, by Claude, or both
Slash command
/dev:verifyThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /verify — Post-Implementation Quality Check You are performing a post-implementation quality check on the current diff. The user has already made changes and wants them reviewed, documented, and prepared for commit. ## Input An optional scope follows this prompt (e.g., "staged", "last commit", a file path). If no scope is given, default to all uncommitted changes (staged + unstaged). ## Step 1: Quality Check (parallel) Launch these agents **simultaneously** using the Task tool: 1. **bug-hunter** — Review the diff for correctness issues. Only report findings with confidence >= 80. 2...
You are performing a post-implementation quality check on the current diff. The user has already made changes and wants them reviewed, documented, and prepared for commit.
An optional scope follows this prompt (e.g., "staged", "last commit", a file path). If no scope is given, default to all uncommitted changes (staged + unstaged).
Launch these agents simultaneously using the Task tool:
bug-hunter — Review the diff for correctness issues. Only report findings with confidence >= 80.
convention-enforcer — Read the project's CLAUDE.md and check the diff against its conventions.
Both agents run in parallel. Wait for both to complete.
After the quality check passes, auto-run:
Present the commit message to the user. STOP and wait for explicit user approval before running git commit or git push. Never commit or push automatically.
npx claudepluginhub danielochoa/ai-coding --plugin dev/verifyRuns verification checks on codebase including types (mypy), lint (ruff), tests (pytest cov), security (pip-audit), secrets, prints, and git status. Outputs summary report with pass/fail and readiness status.
/verifyRebuilds a page from extracted design tokens, pixel-diffs against the live site, and reports a fidelity score. Supports --min for CI gating and --tokens for offline verification.
/verifyVerifies all git-changed files for common mistakes, logic errors, and security issues, outputting per-file summaries with issue counts and severity ratings (CRITICAL, WARNING, INFO).
/verifyRuns comprehensive codebase verification including build, type checks, linting, tests, console.log audit, and git status. Outputs PASS/FAIL report with PR readiness. Supports quick/full/pre-commit/pre-pr modes.
/verifyVerifies implementations or changes using parallel specialized agents with 0-10 grading, full reports across tests/security/quality, and improvement suggestions.
/verifyRun full R verification loop before committing. Checks build, lint, style, test coverage, and code quality.