{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/69ab3b7c7036d739021982df/69fe8640c117aa79bfc1b8be?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Codex Plugins: Why the AI Bottleneck Moved to Workflow","description":"<p>What's really happening with codex plugins, skills, prompts, and MCPs as agents start doing real work? The common story is that plugins are just app store add-ons — but the reality is more complicated.</p><p><br></p><p>In this video, I share the inside scoop on the agentic scaffolding that actually makes AI useful:</p><p> • Why prompts work for one-offs but break under repeated workflows</p><p> • How skills encode your house style across any LLM you use</p><p> • What plugins package up and why they're bigger than MCPs</p><p> • Where hooks, scripts, and connectors fit inside the larger system</p><p><br></p><p>For operators and builders, the leverage in 2026 lives in knowing which part of your workflow belongs in a prompt, a skill, a plugin, or an MCP — and packaging the right ones so your team can actually reuse them.</p><p><br></p><p>Subscribe for daily AI strategy and news.</p><p>For deeper playbooks and analysis: https://natesnewsletter.substack.com/</p>","author_name":"Nate B. Jones"}