Retrospective Agent (Grade A)Skill di dati-ai collaudato per la sicurezza per Claude AI. Voto A. Esegue la retrospettiva dopo ogni completamento di tracciamento per estrarre insegnamenti. Analizza ciò che è stato fatto, ciò che è fallito e quali pattern emergono. Aggiorna il guidatore/conoscenza/patterns.md con nuove soluzioni e l'errore.json con nuovi pattern di errore. Propone anche aggiornamenti delle abilità se si identificano miglioramenti relativi al workflow.

Can I use this alongside other Claude Code plugins?

Yes. SupaConductor uses the /orchestrator-supaconductor: namespace and doesn't conflict with any other plugins, built‑in commands, or MCP servers.

Asked by Jamal Carter · Apr 9, 2026

Is this overkill for small tasks?

For a quick one‑file fix — yes, just use Claude Code directly. Use SupaConductor when the work touches three or more files, you’d normally plan before coding, you want automated quality checks, or you want the work done right the first time. You can also use individual commands without the full loop.

Asked by Bilal Choudhury · Mar 22, 2026

Does this work with Cursor, Windsurf, or other AI tools?

No — SupaConductor is a Claude Code plugin that requires Claude Code's plugin system (agents, skills, slash commands, hooks). However, the conductor/ directory it creates is just Markdown files. Any AI tool can read them, so you can switch tools later and keep your specs, plans, and documentation.

Asked by Quyen Tran · Mar 8, 2026

How much of my context window does this use?

Skills use progressive disclosure — only ~100 tokens each for metadata. Full instructions load only when activated (typically under 5,000 tokens each). The 39 skills are not loaded all at once. Agents run as separate conversations with their own context windows, so they don't fill up your main conversation. Approximate usage: Orchestrator ~4,000 tokens (active during /go); Planner ~3,000 tokens (during planning); Evaluator ~2,500 tokens each (only when active); Board meeting ~5,000 tokens (on‑demand); Idle ~500 tokens (between steps).

Asked by Renata Silva · Feb 28, 2026

How much does this cost in API credits?

SupaConductor uses the same Claude API as normal Claude Code — it just structures the work more carefully. Because it runs multiple agents (planning, execution, evaluation), it uses roughly 3‑5× the API calls compared to doing everything manually in one conversation. SupaConductor optimizes costs automatically: it uses Opus (the most capable model) for planning and evaluation, and Sonnet (faster, cheaper) for execution tasks. Ways to reduce cost: use /orchestrator-supaconductor:implement if you write specs yourself, skip board meetings for small features (they're opt‑in), or use human‑in‑the‑loop mode to stay in control of scope.

Asked by Diego Fernández · Feb 24, 2026