Iteratively refine code artifacts or workspaces by inferring evaluation criteria, deploying judge panels to score and deliberate improvements, generating refined versions from feedback, and tracking progress with regression rollback.
npx claudepluginhub 2389-research/claude-pluginsGenerator subskill for simmer. Produces an improved version of the artifact based on the judge's ASI feedback. Handles both single-file and workspace targets. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
Judge board subskill for simmer. Dispatches a panel of judges with different lenses, runs one deliberation round where they challenge each other's scores, then synthesizes consensus scores + single ASI. Drop-in replacement for simmer-judge that produces identical output format. Do not invoke directly — dispatched by the simmer orchestrator when JUDGE_MODE is board.
Judge subskill for simmer. Scores a candidate artifact against user-defined criteria on a 1-10 scale and produces ASI (highest-leverage direction) for the next generator round. Supports judge-only, runnable evaluator, and hybrid evaluation modes. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.
Reflect subskill for simmer. Records iteration results in trajectory table, tracks best candidate, handles regression rollback, and passes ASI forward to the next round. Supports both single-file and workspace modes. Do not invoke directly — called by simmer orchestrator after each judge round.
Setup subskill for simmer. Inspects the artifact or workspace, infers evaluation contracts and search space, proposes a complete assessment to the user, and produces a setup brief after confirmation. Conversational, not form-based — the agent does the work of understanding the problem, then presents what it found. Do not invoke directly — called by simmer orchestrator.
Claude Code plugins and MCP servers we use at 2389.
Add the marketplace:
/plugin marketplace add 2389-research/claude-plugins
Install plugins individually:
/plugin install css-development@2389-research
/plugin install firebase-development@2389-research
/plugin install terminal-title@2389-research
| Plugin | Description | Documentation |
|---|---|---|
| css-development | CSS development workflows with Tailwind composition, semantic naming, and dark mode by default | README |
| firebase-development | Firebase project workflows including setup, features, debugging, and validation | README |
| terminal-title | Automatically updates terminal title with emoji + project + topic context, plus TodoWrite conventions | README |
This marketplace also lists external MCP servers:
Browse the marketplace: https://2389-research.github.io/claude-plugins
This is a monorepo containing multiple independent plugins. Each plugin:
css-development/, firebase-development/, etc.).claude-plugin/plugin.json configurationSee CLAUDE.md for developer documentation on the monorepo structure and conventions.
mkdir -p new-plugin/.claude-pluginnew-plugin/.claude-plugin/plugin.jsonnew-plugin/skills/new-plugin/README.md and new-plugin/CLAUDE.md.claude-plugin/marketplace.json with new plugin entrynpm run generateSee docs/DEVELOPMENT.md for comprehensive development guide.
Want to chat about these plugins or how we use Claude Code?
Email us: hello@2389.ai
We'd love to hear from you!
Prepare codebases for public/open-source release and audit them for openness - full lifecycle prep or standalone review
Share bugs, ideas, or general feedback.
Non-technical progress summaries for Claude Code work (hides diffs/log noise).
Use this agent when evaluating new development tools, frameworks, or services for the studio. This agent specializes in rapid tool assessment, comparative analysis, and making recommendations that align with the 6-day development cycle philosophy. Examples:\n\n<example>\nContext: Considering a new framework or library
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.