* [Ponytail v4.9.0](https://github.com/DietrichGebert/ponytail) – A plugin that makes AI agents generate minimal, safe, and accessible code by skipping unnecessary steps and using native or existing solutions first.

* [Claude Code Workflows v0.25.0](https://github.com/shinpr/claude-code-workflows) – End-to-end AI-assisted development workflows using specialized agents to plan, implement, and quality-check reviewable code.

* [capcut-cli v0.20.0](https://github.com/renezander030/capcut-cli) – Independent CapCut/JianYing CLI that edits local drafts via JSON in and out, supports multi-timeline synchronization, and enables deterministic inspection and subtitle automation without a server.

* [claude-code-zh-cn v2.13.0](https://github.com/taekchef/claude-code-zh-cn) – Simplified Chinese localization plugin adding UI and installer support for an AI code client.

* [sd0x-dev-flow v4.3.0](https://github.com/sd0xdev/sd0x-harness) – Harness layer for Claude Code that enforces hook-based review anchors, state-machine gates, and fail-closed safety for AI-assisted development.

* [sd0x-dev-flow v4.2.0](https://github.com/sd0xdev/sd0x-dev-flow) – Claude Code plugin enforcing hook-based dual review, auto-fix loops, and fail-closed quality gates.

* [genshijin v1.5.0](https://github.com/InterfaceX-co-jp/genshijin) – Japanese caveman-based ultra-compressed communication skill for Claude Code/Codex agents, optimized for natural Japanese phrasing efficiency.

* [Citadel v1.3.5](https://github.com/SethGammon/Citadel) – Operating layer that turns one-off coding-agent chats into repeatable workflows with durable memory, intent routing, safety hooks, telemetry, and coordinated agents.

* [ponytail 1.1](https://github.com/0xwilliamortiz/ponytail-improved) – An agent skill that uses a ladder-based decision process and two lifecycle hooks to stop unnecessary code over-building while keeping validation and safety checks intact.