feature-purge

Pipeline stage-0 prompt refiner. Runs FIRST — before skills-selector and smart-dispatch — turning a raw idea, pasted draft, or the current chat into a definitive, production-grade prompt (Anthropic prompt-engineering best practices), then hands the refined prompt + an Execution Map (agents, skills, models, effort, time & token estimate) to the routers so they pick the best skills/models with sharpened context. When no file path is given, the input IS the chat/pasted text and the output is returned inline (processed naturally), not forced to a file. Use when the user invokes /senior-prompt-engineer, says "refine my prompt", "improve this prompt", "turn this idea into a prompt", "rewrite idea.md to prompt.md", "definitive prompt", "professional prompt", or pastes a draft prompt/idea to be hardened. Cross-CLI: Claude, Codex, Gemini, OpenCode, Antigravity (agy), lemon-code (lemon).

OpenAPI spec management hub. Maintains versioned API specs, validates specs on every commit, detects breaking changes between versions, generates typed clients (TypeScript, Python, Go), publishes developer documentation (Redoc/Swagger UI), and exports Postman collections. Enforces spec-first development workflow.

Async and concurrency static analysis plugin. Scans TypeScript/JavaScript codebases for race conditions, unbounded Promise.all, missing AbortController, swallowed rejections, and N+1 async patterns. Runs as a pre-commit hook or CI check and provides inline fix suggestions.

Load testing orchestration plugin. Manages k6 and Artillery test suites, schedules nightly soak tests, stores historical performance baselines, detects performance regressions between releases, and generates Grafana-compatible performance reports. Tracks p50/p95/p99 trends over time.

Reusable closed loop for exploratory QA over any live web app, driven by Claude via the Chrome DevTools MCP with four expert lenses (QA, Product, Engineering, Security). Read-only on production, writes one markdown report per finding immediately, and hands reviewed findings to a triage agent that emits prioritized tasks + per-fix PLAN stubs.

Wrapper that bridges the AI harness to external CLIs — captures help output, documents commands, saves input/output token metrics, and provides a standardized interface so the harness invokes CLIs without context bloat.

Project and workspace AI setup orchestrator. Builds AGENTS.md/CLAUDE.md contracts, optional global or project skills, Spotify Squad-style agent/subagent topology, and adversarial setup review for single apps, monorepos, and multi-domain workspaces.

Agentic Value Loops plugin — Continuous improvement engine that ships verified increments with constant quality. Includes loops for Feature Development, Maintenance & Security, Documentation Sync, and AI Tuning.

WCAG 2.1 AA/AAA accessibility audit for web components, pages, and apps. Detects contrast failures, missing ARIA labels, keyboard trap issues, focus order problems, and screen-reader gotchas. Use when user wants to audit accessibility, fix a11y warnings, prepare for compliance review, or validate UI against WCAG standards.

Configures token-saving tools (rtk, caveman, graphify, context-mode) globally or per project. Allows auditing and calculating the token savings obtained.