Agent Toolkit
Install when you want one marketplace to invoke Codex, Gemini, Perplexity, and dozens of other model CLIs from Claude Code without rewriting orchestration each time.
Overview
agent-toolkit is a plugin marketplace for the Build phase that wires Claude Code to Codex, Gemini, Perplexity, and 53 other model CLI skills for orchestrated coding work.
What is this marketplace?
- 56-plugin agent-toolkit marketplace from softaworks for Claude-style agent hosts
- codex plugin routes OpenAI Codex CLI (codex exec, codex resume) with GPT-5.2 default for edits
- gemini plugin targets Gemini 3 Pro for plan review and >200k context code review
- perplexity and additional ai-tools category plugins extend research and analysis
- Each plugin ships paired skills under dist/plugins paths with strict false for flexible invocation
- 56 plugins in the agent-toolkit marketplace
- Named first-wave plugins include codex (GPT-5.2 default), gemini (Gemini 3 Pro default), and perplexity in ai-tools cate
Community signal: 2k GitHub stars.
What problem does it solve?
Switching between Codex, Gemini, and Perplexity manually breaks flow when one agent session should pick the right model CLI for each subtask.
Who is it for?
Power users running Claude Code who already pay for OpenAI, Google, and Perplexity CLIs and want marketplace-native skill entrypoints.
Skip if: Builders who only use a single in-editor model with no external CLIs or who need non-AI DevOps plugins exclusively.
What do I get? / Deliverables
After registering agent-toolkit, you enable targeted plugins so Claude routes exec, review, and research work to the matching vendor CLI with bundled skills.
- Selectable set of up to 56 AI CLI plugins with paired skills
- Codex-driven refactor and exec pathways
- Gemini and Perplexity-backed review and research invocations
Plugins in this marketplace
56 plugins — install individually after you add the marketplace.
PluginVersion
CodexUse when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.—GeminiUse when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.—PerplexityWeb search and research using Perplexity AI. Use when user says 'search', 'find', 'look up', 'ask', 'research', or 'what's the latest' for generic queries.—Agent Md RefactorRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.—Command CreatorCreate Claude Code slash commands. Use when users ask to 'create a command', 'make a slash command', 'add a command', or want to document a workflow as a reusable command.—Plugin ForgeCreate and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.—Skill JudgeEvaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages.—Backend To Frontend Handoff DocsCreate API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration.—C4 ArchitectureGenerate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document system architecture, visualize software structure.—Crafting Effective ReadmesUse when writing or improving README files. Provides templates and guidance matched to your audience and project type.—Draw Iodraw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG conversion, layout adjustment, and AWS icon usage.—ExcalidrawUse when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization.—Frontend To Backend RequirementsDocument frontend data needs for backend developers. Use when frontend needs to communicate API requirements to backend.—Marp SlideCreate professional Marp presentation slides with 7 beautiful themes. Use when users request slide creation, presentations, or Marp documents.—Mermaid DiagramsComprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams.—Writing Clearly And ConciselyUse when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.—Design System StarterCreate and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates.—MuiMaterial-UI v7 component library patterns including sx prop styling, theme integration, responsive design, and MUI-specific hooks.—Openapi To TypescriptConverts OpenAPI 3.0 JSON/YAML to TypeScript interfaces and type guards. Use when generating types from OpenAPI or creating API interfaces.—React DevBuild React components with TypeScript. Covers type-safe patterns for React 18-19 including generic components, proper event typing, and routing integration.—React UseeffectReact useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.—Database Schema DesignerDesign robust, scalable database schemas for SQL and NoSQL databases. Provides normalization guidelines, indexing strategies, migration patterns.—Dependency UpdaterSmart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions.—Naming AnalyzerSuggest better variable, function, and class names based on context and conventions.—Reducing EntropyManual-only skill for minimizing total codebase size. Only activate when explicitly requested. Measures success by final code amount.—Session HandoffCreates comprehensive handoff documents for seamless AI agent session transfers. Use when context window approaches capacity or work session is ending.—Lesson LearnedAnalyze recent code changes via git history and extract software engineering lessons. Use when reflecting on work or asking 'what is the lesson here?'—Game Changing FeaturesFind 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking or wants to find high-impact features.—GepettoCreates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.—Requirements ClarityClarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear or features are complex.—Ship Learn NextTransform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework.—Difficult Workplace ConversationsStructured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework.—Feedback MasteryNavigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) technique.—Daily Meeting UpdateInteractive daily standup/meeting update generator. Use when user says 'daily', 'standup', 'scrum update', 'status update', or wants to prepare for daily meeting. Conducts interview (yesterday, today, blockers, discussion topics) and optionally pulls activity from GitHub/git/Jira if available and approved by user.—Professional CommunicationGuide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences.—Qa Test PlannerGenerate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers.—Commit WorkCreate high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits).—Datadog CliDatadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use when debugging production issues or working with Datadog observability.—Domain Name BrainstormerGenerates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.).—HumanizerRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.—Meme FactoryGenerate memes using the memegen.link API. Use when users request memes, want to add humor to content, or need visual aids for social media.—Web To MarkdownConverts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.—JiraUse when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.—Agent Ascii Ui Mockup GeneratorVisualize UI concepts through ASCII mockups before implementation. Creates multiple ASCII mockup variations for dashboard layouts, forms, and other UI components.—Agent Codebase Pattern FinderFind similar implementations, usage examples, or existing patterns in the codebase. Provides concrete code examples based on what you're looking for.—Agent Communication Excellence CoachReview communication drafts or prepare difficult conversations. Provides email refinement, tone calibration, roleplay practice, and presentation feedback.—Agent General PurposeDefault agent for handling complex, multi-step tasks with automatic delegation capabilities.—Agent Mermaid Diagram SpecialistMermaid diagram specialist for creating flowcharts, sequence diagrams, ERDs, and architecture visualizations.—Agent Ui Ux DesignerExpert UI/UX design critic and advisor who provides research-backed, opinionated feedback on interfaces. Pushes back on bad ideas and cites sources.—Command Codex PlanCreate a detailed implementation plan using Codex 5.2 with high reasoning.—Command Compose EmailDraft a professional email using the What-Why-How framework. Use when composing emails to colleagues, stakeholders, or leadership.—Command Explain Changes Mental ModelBuild a mental model of changes by splitting them into smaller logical chunks.—Command Explain Pr ChangesGenerate comprehensive markdown summary of pull request changes with visual impact analysis.—Command Sync BranchSync feature branch with the latest main branch.—Command Sync Skills ReadmeSync root README.md with current skills inventory from skills/ directory.—Command Viral TweetTransform a raw tweet idea into an optimized viral post for X. Analyzes engagement drivers and generates 3 optimized versions with posting strategy.—Recommended Marketplaces
1NoBeef1 Marketplace1NoBeef1/1NoBeef1-marketplace
3 Surgeons Marketplacesupportersimulator/3-surgeons
A5c.Aia5c-ai/babysitter-claude
Aevccaevelop/aevcc
Agent Engineering Toolkitrodrigorjsf/agent-engineering-toolkit
Agent Operatorshtxryan/agent-operators
Journey fit
Primary fit
Build agent-tooling is the canonical shelf because the pack standardizes how coding agents call external model CLIs during implementation and review loops. Agent-tooling reflects multi-model dispatch (Codex exec/resume, Gemini large-context review, Perplexity research) rather than a single app feature.
How it compares
Multi-model CLI orchestration marketplace, not a lone MCP server or domain-specific vertical pack.
Common Questions / FAQ
Who is Agent Toolkit for?
It is for solo developers orchestrating multiple AI coding and research CLIs from Claude Code via consistent skill wrappers.
When should I use Agent Toolkit?
Use it when tasks explicitly call for Codex exec/resume, Gemini large-context review, Perplexity lookups, or sibling plugins in the 56-plugin catalog.
How do I add Agent Toolkit to my agent?
Add softaworks/Agent Toolkit as a Claude marketplace, install only the plugins you need (codex, gemini, perplexity, etc.), and ensure each vendor CLI is authenticated on the host.