By settlemint
Modern development tools for React, APIs, blockchain, databases, and testing. MCP-first skills with Context7 integration for up-to-date documentation.
npx claudepluginhub settlemint/agent-marketplace --plugin devtoolsHeadless browser automation CLI for AI agents using ref-based element selection. Routes between agent-browser, Playwright MCP, and Claude Chrome integration.
oRPC API routes with 5-file pattern. Use when asked to "create API route", "add API endpoint", or "build type-safe API". Only for projects using oRPC.
Mass rename/replace across codebase. Use when user asks to rename functions, replace patterns, or refactor code across files. Better than grep for code changes.
Better Auth library patterns. Use when asked to "setup authentication", "add passkey login", or "configure social auth". Only for projects using better-auth package.
Create a feature branch with naming convention. Use when asked to "create branch", "new branch", or "start feature".
Systematic code health audit for YAGNI, dead code, duplication, and technical debt
Patterns for using Codex MCP for deep code reasoning, security analysis, and architecture review
Create a conventional commit. Use when asked to "commit changes" or "save my work".
Enforce a precise, minimal design system inspired by Linear, Notion, and Stripe. Use when building dashboards, admin interfaces, or any UI that needs Jony Ive-level precision - clean, modern, minimalist with taste. Every pixel matters.
Drizzle ORM patterns for PostgreSQL schemas, queries, migrations, and Zod integration. Triggers on drizzle, pgTable, db.select, db.insert, migration.
Git workflows - commits, branches, PRs. Routes to specialized skills based on task.
Kubernetes Helm chart development. Use when asked to "create helm chart", "configure kubernetes deployment", or "add helm template". Covers values.yaml, templates, and subchart patterns.
Internationalization with i18next. Use when asked to "add translations", "internationalize app", or "support multiple languages". Covers translation setup, namespaces, pluralization, and language detection.
Motion (formerly Framer Motion) for React animations. Use when asked to "add animation", "animate component", or "create transition". Covers transitions, gestures, layout animations, and exit animations.
Pino fast JSON logger for Node.js. Use when asked to "add logging", "setup structured logging", or "configure logger". Covers log levels, child loggers, transports, and redaction.
Playwright E2E testing. Use when asked to "write E2E test", "test user flow", or "automate browser testing". Covers Page Object pattern, web-first assertions, and proper locators.
Create a pull request with smart defaults. Use when asked to "create PR", "open pull request", or "submit for review".
Push commits to remote with smart QA check. Use when asked to "push changes", "push to remote", or "upload commits".
Radix UI primitives for accessible React components. Use when asked to "create modal", "add dropdown menu", or "build accessible dialog". Covers dialogs, dropdowns, popovers, and form controls.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
React 19 components with Tailwind CSS v4. Use when asked to "create component", "build form", or "add data table". Covers shadcn/ui, forms, tables, routing, and data fetching.
Recharts for React data visualization. Use when asked to "create chart", "visualize data", or "add dashboard chart". Covers line, bar, area, pie charts with responsive containers.
Restate durable execution for fault-tolerant services. Use when asked to "build durable workflow", "create fault-tolerant service", or "implement saga pattern". Covers ctx.run, ctx.sleep, and awakeables.
Multi-pass convergence pattern for designs, plans, implementations, and reviews. 5 iterations until quality converges.
shadcn/ui component library with MCP server integration. Use when adding UI components, building forms, or working with shadcn primitives. Triggers on shadcn, @/components/ui, cn(), radix, cva, component variants.
Solidity smart contract development with Foundry. Use when asked to "write smart contract", "create token", or "deploy contract". Covers writing, testing, security, deployment, and upgrades.
Sync branch with main and resolve conflicts. Use when asked to "sync with main", "merge main", "update branch", or "pull latest".
TanStack Start full-stack React framework. Use when asked to "create route", "add file-based routing", "implement SSR", or "create server function". Covers file-based routing, SSR, data loading, and server functions.
TDD TypeScript workflow. Use when asked to "write tests first", "test-driven development", or "red-green-refactor". RED-GREEN-REFACTOR cycle for all new TypeScript code.
Terraform/OpenTofu infrastructure as code patterns. READ-ONLY - Claude NEVER executes terraform commands.
TheGraph subgraph development with AssemblyScript. Use when asked to "index blockchain events", "create subgraph", or "query on-chain data". Covers schema definitions, handlers, and Matchstick testing.
Structured debugging workflow. Use when asked to "help debug", "fix this error", or "troubleshoot issue". Systematic approach for identifying root causes.
Turborepo monorepo build system. Use when asked to "setup monorepo", "configure build pipeline", or "add turbo caching". Covers task pipelines, caching, and package management.
Language Server Protocol tools for code navigation, type analysis, and semantic code understanding
Check web interfaces against Vercel's design guidelines. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", "check my site against best practices", or "apply Vercel design guidelines".
Viem blockchain client patterns for Ethereum. Use when asked to "interact with blockchain", "send transaction", or "read smart contract". Covers transactions, signing, encoding, and contract calls.
Vitest unit testing patterns for TypeScript. Use when asked to "write unit tests", "mock dependencies", or "add test coverage". Covers test structure, mocking, assertions, and coverage.
Zod v4 schema patterns. Use when asked to "validate input", "add form validation", or "create schema". For projects using Zod validation library.
SettleMint development tools for Claude Code.
Claude is smart. It has excellent built-in capabilities for planning, coding, and problem-solving. These plugins don't replace Claude's intelligence—they enhance it.
Our approach:
.claude/ for analysis, generating learnings that feed back into plugin improvementsAfter installing the plugins, the typical development flow is:
/plan → Use Claude's built-in plan mode
→ Review and accept the plan
→ Claude implements the changes
/pr → Create a pull request
/fix-pr-reviews → Address reviewer feedback
One-line setup (recommended):
curl -fsSL https://raw.githubusercontent.com/settlemint/agent-marketplace/main/setup.sh | bash
This installs dependencies, configures marketplaces, and installs the full plugin suite.
Interactive (inside Claude Code):
/plugin marketplace add settlemint/agent-marketplace
/plugin install devtools@settlemint
/plugin install flow@settlemint
Or add to your project's .claude/settings.json:
{
"extraKnownMarketplaces": {
"settlemint": {
"source": {
"source": "github",
"repo": "settlemint/agent-marketplace"
}
}
},
"enabledPlugins": {
"devtools@settlemint": true,
"flow@settlemint": true
}
}
Modern development tools with MCP-first skills. Uses Context7 for up-to-date library documentation.
Slash Commands:
| Command | Description |
|---|---|
/commit | Create a conventional commit |
/branch | Create a feature branch |
/pr | Create a pull request |
/push | Push with smart QA check |
/sync | Sync branch with main |
Skills:
| Skill | Domain | MCP Source |
|---|---|---|
react | React 19 components, Tailwind v4 | Context7 |
tanstack-start | Full-stack React framework | Context7 |
radix | Accessible UI primitives | Context7 |
shadcn | shadcn/ui components | Shadcn MCP |
api | oRPC API routes | OctoCode |
drizzle | Drizzle ORM, PostgreSQL | Context7 |
zod | Zod v4 schemas | Context7 |
viem | Ethereum blockchain client | Context7 |
solidity | Smart contracts, Foundry | OctoCode |
vitest | Unit testing | Context7 |
playwright | E2E testing | Playwright MCP |
thegraph | TheGraph subgraphs | OctoCode |
helm | Kubernetes Helm charts | OctoCode |
turbo | Turborepo builds | Context7 |
restate | Durable execution | Restate MCP |
better-auth | Authentication | OctoCode |
i18n | Internationalization (i18next) | Context7 |
motion | Animations (Motion/Framer) | Context7 |
recharts | Data visualization | OctoCode |
pino | Structured logging | OctoCode |
terraform | Infrastructure as code | - |
tdd-typescript | Test-driven development | - |
troubleshooting | Debug patterns | - |
agent-browser | Headless browser automation | - |
ast-grep | Mass rename/replace | - |
code-health | Code health audit | - |
codex-patterns | Deep code reasoning | Codex MCP |
design-principles | Linear/Notion/Stripe design | - |
react-best-practices | React/Next.js performance | - |
rule-of-five | Multi-pass convergence | - |
typescript-lsp | LSP code navigation | - |
vercel-design-guidelines | UI review | - |
Hook-based workflow automation that enhances Claude's native capabilities.
Slash Commands:
| Command | Description |
|---|---|
/fix-pr-reviews | Fix PR review comments and resolve threads |
Skills:
| Skill | Description |
|---|---|
init-enhanced | Deep codebase analysis with progressive disclosure docs |
fix-pr-reviews | Address reviewer feedback with educational responses |
Hooks:
The flow plugin uses hooks to enhance Claude's behavior without replacing it. Hooks fire on specific events and add context or trigger actions.
Configure in .claude/settings.json under the env key:
| Variable | Values | Default | Purpose |
|---|---|---|---|
FORCE_AUTOUPDATE_PLUGINS | "1" / "0" | Disabled | Force reinstall all plugins on startup |
Example:
{
"env": {
"FORCE_AUTOUPDATE_PLUGINS": "1"
}
}
MIT
Essential development workflow agents for code review, debugging, testing, documentation, and git operations. Includes 7 specialized agents with strong auto-discovery triggers. Use when: setting up development workflows, code reviews, debugging errors, writing tests, generating documentation, creating commits, or verifying builds. [Role] specialist. MUST BE USED when: [trigger 1], [trigger 2], [trigger 3]. Use PROACTIVELY for [broad task category].
Executes bash commands
Hook triggers when Bash tool is used
External network access
Connects to servers outside your machine
Runs pre-commands
Contains inline bash commands via ! syntax
Share bugs, ideas, or general feedback.
Custom commands, skills, and agents for Claude Code - session continuity, 23 expert agents, 71 skills, 3 commands, 6 rules, 4 hooks, 13 output styles, modern CLI tools
Advanced React skills for hooks, context, and performance optimization.
Optimizes context usage and improves Claude integration performance. Targets React development workflows.
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
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.