Craft quality software with AI discipline. Spec-driven development plugin for Claude Code and Opencode — quality gates, adversarial testing, and evidence capture.
Runs configured build and test commands in tiered order. Captures output as evidence per tier. Returns PASS, FAIL, WARN, or SKIP based on per-tier verdicts. Internal gate — invoked by verify, not directly by users.
Detects leaked secrets, injection patterns, and sensitive data exposure across changed files. Uses real tooling when configured, LLM judgment for analysis. Internal gate — invoked by verify.
Maps every acceptance criterion from the spec to implementation evidence and test evidence. Criteria without evidence fail. The ultimate quality gate. Internal — invoked by verify.
Periodic codebase health check. Analyzes architecture, complexity, consistency, and debt across the full codebase. Produces persistent findings in AUDIT.md.
Investigation-first debugging workflow. Scopes the problem, delegates root cause analysis, produces a diagnosis report, and applies fix/log/defer autonomously.
Specwright health check. Validates shared config, anchor docs, workflow and session state, commands, gates, and hooks. May backfill shipped PR metadata when it can prove the mapping safely.
Detects project stack and existing guardrails, then interactively configures deterministic quality checks across session, commit, push, and CI/CD layers.
Captures patterns and learnings from the current work unit. Reviews build failures, gate findings, and architecture decisions. Applies objective promotion criteria autonomously — patterns.md is the artifact.
Shows current Specwright state for this worktree, the attached work, repo-wide active works, gate results, and lock status. Supports --reset, --cleanup, and --repair {unitId}.
Syncs the local repository by fetching all remotes, updating the base branch, and removing stale local branches that are not protected by live sessions or helper worktrees.