ArchitectPlaybook

Audit a TypeScript/React frontend against an opinionated WCAG 2.2 AA baseline (tooling, component patterns, application shell) with optional implementation plan.

Audit a project's agentic instruction files (CLAUDE.md, AGENTS.md, .cursor/rules, .cursorrules, .github/copilot-instructions.md, Windsurf, Aider) and Claude Code settings (.claude/settings.json, .claude/settings.local.json) against an opinionated baseline covering project context coverage, operational guidance, settings hygiene, and multi-agent drift. Static-only with optional implementation plan.

Graphify-powered architectural audit of a TypeScript codebase. Produces a diagnostic snapshot + checks module boundaries, coupling, state/data flow, and conventions, with optional implementation plan.

Audit build pipeline and bundle output (static-first with optional --with-stats enrichment). Checks configuration, composition, hygiene, and performance with optional implementation plan.

Audit Node.js dependency tree (security, health, compliance, hygiene). Static-first with optional --with-network enrichment for vulnerabilities, outdated, and abandonment data. Optionally generates an implementation plan.

Audit project documentation against an opinionated baseline spanning onboarding, architectural/decision docs, code-level docs, and operational documentation with drift detection. Static-first with optional --with-link-check. Optionally generates an implementation plan for the gaps.

Audit a TypeScript codebase's error-handling discipline against an opinionated baseline spanning throw and catch hygiene, async and network error handling, React error boundaries, and logging and observability. Static-only by design. Optionally generates an implementation plan for the gaps.

Audit a TypeScript project's lint configuration against an opinionated baseline spanning configuration shape, rule coverage, strictness and enforcement, and suppressions hygiene. Auto-detects ESLint or Biome. Static-first with optional --with-run enrichment. Optionally generates an implementation plan for the gaps.

Audit runtime performance patterns in a TypeScript/React frontend (render, network/data, assets/CWV, main-thread). Static-first with optional --with-lighthouse-results enrichment and implementation plan.

Audit pre-commit, pre-push, and CI/CD quality gates against an opinionated baseline. Reports present/missing/misconfigured gates and optionally generates an implementation plan.

Audit idiomatic React (hooks correctness, component design, state management, React 18/19 idioms). Static-only by design with optional implementation plan.

Audit a TypeScript project's type discipline against an opinionated baseline spanning compiler configuration, type quality in source, type system usage, and type safety at IO boundaries. Static-first with optional --with-run enrichment from tsc --noEmit. Optionally generates an implementation plan for the gaps.

Use before completing work or opening a pull request in this repository.

Audit a TypeScript and React frontend against an opinionated security baseline spanning authentication/sessions, input handling and XSS prevention, transport/headers/cookies, and secrets/data protection/third-party integrations. Frontend-only. Static-first with optional --with-scan enrichment. Optionally generates an implementation plan for the gaps.

Audit React tests against Testing Library query priority and well-known React Testing Library pitfalls. Static-first with optional --with-run coverage enrichment and implementation plan.

Perform a principles-based architectural pull request review using Ben's judgement, then ask whether to post it as pending or submit it on GitHub.

Detect optional enrichment tooling for architect-playbook audits and optionally install missing development dependencies and scaffold project configuration. Read-only by default; mutation is gated behind --install and --scaffold-configs and prompts before every change.

The meta-improvement layer of the architect-playbook. Reads a review's gap report (or a user-supplied gap, or audit-history patterns), locates the affected SKILL.md and adjacent files, and proposes a minimal reversible edit to the playbook so the same class of gap is more likely to be caught next time. Dry-run by default; --apply enables mutation but always prompts for confirmation.

Copy every architect-playbook skill into ~/.claude/skills/ so the slash commands are available in every Claude Code session on this machine.

Copy every architect-playbook skill into the current project's .claude/skills/ directory so the slash commands are available inside this project only.

One-time, idempotent preparation that every architect-playbook audit depends on. Verifies graphify is installed, builds the project knowledge graph, and merges the graphify-aware PreToolUse hook into the project's .claude/settings.json.