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.
Persistent, cross-session memory for OpenAI Codex, powered by Honcho from Plastic Labs. Lifecycle hooks capture each session and inject the relevant context back at session start, so Codex remembers your preferences, projects, and decisions across restarts and context resets.
Bundle of 8 Threads (Meta) marketing skills for Claude Code and Codex with Threads-native hook formulas, single-post and multi-post thread writing, a unified humanizer (rewrite plus `--mode audit` pre-publish check), viral hook extraction, reply and quote drafting, and a weekly content planner. Posts and threads ship via Publora, which auto-splits long content into a connected multi-post thread.
Evidence-backed, route-neutral research planning, exploration, and execution with explicit Claims, Evidence, failure polarity, recovery, lifecycle, and human-controlled promotion boundaries.
Architecture canon for Flutter apps built on yx_scope, yx_state and yx_navigation: layer rules, Data-Domain boundaries, the ViewModel contract, embeddable feature-facade contracts, and three review and planning procedures. The API of each package is covered by the skill that ships inside that package.
Praxen — agent behavior verifier. Compares an agent's declared policy against the available evidence (source, deployment state, or behavioral artifacts); reports where observed behavior diverges from declared intent.
Report UI fixes from the iOS simulator, from Swift, React Native and Flutter apps, and from the Android emulator for React Native and Flutter, straight into your Claude Code session.
Live web search for AI agents. Find current pages, read any URL, and run research agents that work across many sources and return findings with citations. Includes reusable Extraction Templates for consistently shaped records from known sites, and Web Search Agents for research, enrichment, and dataset building.
MotherDuck skills for agents and developers: use the CLI and Guides, explore schemas, write DuckDB SQL, build Dives and Flights, and ship analytics apps and pipelines.
Пять MCP-серверов над API Wildberries (307 методов), Ozon (491), Ozon Performance (45), Яндекс Маркета (165) и Авито (64). Числа из реального API, safety-гейт на запись, авто-пагинация, мультикабинет, поиск по-русски. | Five MCP servers over the Wildberries, Ozon, Yandex Market and Avito Seller APIs: 1072 schema-driven methods, write safety gate, real-API numbers.
Annotate a running iOS simulator in the browser and hand each note to your agent: sim-agentation itself, its MCP server, and skills for working through annotations and adding the SimAgentationPlus SDK.
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.