Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Kin keeps a living map of the software itself so humans and agents can understand what every change touches. Locate, search, context packs, data-flow tracing, and impact analysis without raw file search.
Kin is a graph-native code repository for AI agents and the people who build with them. Its MCP server lets your agent look up callers, references, history and what a change might affect, from the same record you inspect with the kin CLI.
Query Cadence, Altium, KiCad and Universal Netlist designs through the universal-netlist MCP server, which the plugin connects, with a skill for its command line where MCP is unavailable. Needs the universal-netlist binary on PATH.
Give your coding agent design taste. Inspects the existing frontend, commits to a project-specific design direction, scouts curated human-designed component sources (Beautiful UI, beUI, Rare UI, Transitions.dev, shadcn/ui), evaluates fit and dependency cost, and adapts the best-fitting pieces into the app's own design language instead of pasting a theme over it. Ships a catalog of committed design briefs, concrete motion defaults, and an anti-slop audit run against a real render.
EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.
Give your AI agent 600,000+ real app screens, and the skills to use them. Includes the Mobbin MCP and a skill that redesigns your screen from patterns real apps ship, in your own design system, with the references behind every change.
Command-line orchestrator for coding agents that creates a dedicated branch/worktree per task, delegates to Pi and Codex subagents, and enforces typed task, validation, merge, and release-readiness boundaries with receipt-backed repository changes.
Connect your agent to Dataiku: inspect projects, datasets, recipes, ML, and agents with typed MCP tools, and drive Dataiku Cobuild to build project-level assets.
Connect your agent to Dataiku: inspect projects, datasets, recipes, ML, and agents with typed MCP tools, and drive Dataiku Cobuild to build project-level assets.
Author, validate, review and release LinkML schemas with the ohi CLI (ohi linkml). Covers schema authoring, bootstrapping from RDFS/OWL/SHACL/JSON Schema/XSD or sample data, modelling-quality review, instance-data validation, and GitHub Actions setup. Auto-load for any task involving a LinkML schema.
Generate NotebookLM artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables) from your notebooks. Use when the user wants to create any NotebookLM Studio output from their uploaded sources.