205 boosters for "codex" — open source, verified from GitHub, ready to install
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", "description": "Animated data-flow diagrams your AI agent can write. Written by AI. Watched by humans.", "name": "Naor Sabag",
1. 架构不是「画」出来的,是从约束里「逼」出来的。 没搞清约束就画图,画什么都是瞎画。 2. 没有银弹,只有取舍。 任何决策本质都是「用 A 换 B」。一个「没有缺点」的方案,不是完美,是没想清楚。 3. 没有「最好的架构」,只有「在这组约束下最合适的架构」。 同样是聊天,内部工具和微信的答案天差地别。
"name": "agentkernel", "description": "Run commands in secure, isolated sandboxes using agentkernel", "author": "Paul Thrasher",
"name": "@firfi/huly-mcp", "version": "0.40.1", "description": "Huly MCP: feature-complete MCP server for Huly integration",
"name": "sentinelx-prime", "description": "Stage-aware security guidance for planning, risky implementation changes, review, and release checkpoints.", "name": "Alican Kiraz"
"description": "Fuse the Claude Code model with OpenAI Codex and agy: query all three in parallel, then Claude judges, synthesizes, and acts.", "author": { "name": "junkim", "email": "junkim100@gmail.com" }, "homepage": "https://github.com/junkim100/gavel",
"name": "codex-bridge", "description": "Bidirectional bridge between Claude Code and OpenAI Codex CLI. Two AI agents, one conversation.", "keywords": ["codex", "claude", "bridge", "agent-to-agent", "channel", "mcp"]
"name": "trueline-mcp", "description": "Truth-verified file editing for AI coding agents via MCP", "url": "https://github.com/rjkaes"
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", "name": "session-orchestrator", "description": "Session-level orchestration — wave planning, VCS integration, quality gates, persistence, and safety checks",
Agent Tower Plugin enables developers to orchestrate multiple AI coding assistants (Claude, Codex, Gemini) in council, debate, and consensus workflows within Claude Code for richer problem-solving perspectives. It's useful for teams and individual developers seeking diverse AI viewpoints on complex coding tasks.
"name": "swing-skills", "description": "6 cognitive firewalls for AI coding agents. Defends against premature closure, hallucination, anchoring bias, confirmation bias, black-box reasoning, and optimism bias.", "name": "whynowlab",
A TUI-style MCP server that enables Claude and other AI models to ask users questions interactively through a web interface, useful for developers building interactive AI applications that need user input during execution.
"name": "learnship", "description": "Agentic engineering done right — 49 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.", "name": "Favio Vazquez",
You are reviewing frontend code to find the patterns that make a UI look AI-generated ("AI slop"), then rewriting it around one intentional design direction. This is the design counterpart to the skill. It targets two stacks: plain HTML/CSS/JS and React + Tailwind + shadcn/ui. The point is not to c
The ultimate design skill for producing distinctive, production-grade frontend interfaces, visual artifacts, and design systems. This skill consolidates best practices from Anthropic's frontend-design, canvas-design, algorithmic-art, and theme-factory skills, Impeccable's 7-domain reference system,
Execute verbatim. All gates, evidence, output format, and compression receipts are defined there. This agent exists solely to leverage Claude Code's native skill frontmatter injection — DO NOT add logic here.
"version": "0.1.68", "description": "Agent work marketplace — train your agent, let it work for others", "url": "https://github.com/lhead/akemon"
This booster teaches AI assistants how to build vvvv gamma editor extensions, covering file naming conventions, command registration, window types, and API access patterns. It's essential for developers creating custom editor plugins and automation tools in the vvvv visual programming environment.
Self-configuring content creation pipeline. Creates SEO & GEO-optimized content matched to your project and brand voice, then validates with geo-lint until clean. For project-specific rules (components, file naming, categories), the skill
An autonomous coding agent that delegates tasks to Codex CLI with configurable risk modes (full-auto, sandbox, YOLO) to iteratively debug and test code until it passes. Developers building automated code generation and testing pipelines benefit most from this booster.
