go-quality

Git tooling — worktree workflows, default-branch commit prompt, worktree edit-path guard, wt-done merged-branch cleanup, gh-resolve-threads PR review-thread triage, PR-aware push reminders, and on-demand CI + release status watching

Archive Claude Code session transcripts to local and remote targets (S3, rsync/NAS, or any command) on session end — per-machine configurable, nothing hardcoded

Ansible quality gates — diff-scoped ansible-lint + ansible-playbook --syntax-check on modified playbooks/roles, plus a warn-only vault-plaintext check, mirroring CI. Warn-skips on a broken lint env instead of false-blocking. Includes an /ansible skill carrying recent ansible-core/ansible-lint reference in context.

Preferred GitHub repository standards, audited/applied with `gh` — a repo-settings baseline (wiki/projects off, auto-delete merged branches, read-only workflow token, SHA-pinned actions, Dependabot security updates), three branch-ruleset classes, a Dependabot version-updates config, a lightweight tier for content/asset/config repos, and the README/CONTRIBUTING/CLAUDE.md doc split. Ships templates plus a read-only repo-standards-auditor agent for per-repo (fan-out) conformance audits.

Search and analyze past Claude Code session transcripts — sessions CLI for listing, grepping, rendering, and tool-usage stats over the ~/.claude JSONL history

Grafana dashboard creation, management, and quality review for Kubernetes deployments

OpenTofu quality gates — auto-format on edit, and format-check + validate modified config on stop, mirroring CI. Includes a /tofu skill carrying recent-release summaries in context.

Dynamic review team composition with 14 stack-agnostic specialist agents (including a workflow-first UX/interaction evaluator, an adversarial devils-advocate, a pre-publication safety auditor, and a Claude Code config reviewer) for collaborative, multi-angle review using Claude Code agent teams

Task-ownership orchestration — delegate a task (or several) into a hierarchy where one owner agent runs each task end-to-end and orchestrates its own subagents (explore → implement → verify)

Rust quality gates — auto-format, clippy, test, and audit on every turn