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.
AI-native schematic design agent, purpose-built for KiCad (zero-dependency pure-stdlib Python CLI): author and edit .kicad_sch from JSON op-lists with net-diff safety rails, run ERC/design/intent/BOM checks, simulate on KiCad's bundled ngspice, source real parts and fetch datasheets, and import Altium .SchDoc/.SchLib/.PcbDoc read-only into the KiCad flow.
Staged TTNN model bring-up with vLLM TT plugin serving; requires tt-autodebug. Codex runs add optional telemetry when tenstorrent/ar-dashboard is accessible.
MovScript daemon runtime, admin/system management, project/domain planning, review, media query, AI generation, timeline compile, and Electron media editing tools backed by a headless MCP host.
Icons8 icons and Ouch! illustrations for coding agents, plus a design pass over what the agent built with them. Locks a project to one icon pack and one illustration style, rejects wrong metaphors and generic art, and checks the finished screen for emoji standing in for icons, missing images, dead placeholders, broken icon imports, keyboard reach, contrast and token drift, fixing what it finds from the catalogue. Bundles the Icons8 MCP server. Animates static SVG illustrations into looped Lottie and MP4.
Make your agents' reasoning explicit, persistent, and deterministically checkable. Connect decisions to evidence and assumptions, and see what needs another look when a recorded premise changes.
Context-aware AI collaboration skills and implementation loop prompts for creating and validating user context, project AGENTS.md files, and skill artifacts across LLM providers.
A Rust-native agentic memory substrate built on the selene-db graph engine: a bi-temporal knowledge graph, hybrid retrieval, and an optional MCP server.
Skills that take a coding agent from your first trace to evals you can trust: error analysis, datasets, validated graders, eval runs, and production monitoring.
Dev skills I use day to day in agentic engineering, focused on multi-agent-driven work modes and long-horizon autonomous tasks. Includes long-horizon, fan-out, handoff, ctx-research, ctx-grill, to-ctx, just-ask, and the lowband and readout modes.