# Claude Code & Coding Agents — Maximem field notes

> Getting more out of coding agents: Claude Code skills, plugins, hooks and subagents, Cursor rules, Codex workflows and the tools engineers add to them.

Coding agents stopped being autocomplete once they could run commands, read a repository and load instructions on demand. The real gains now come from their extension points; a well-written skill or plugin changes what Claude Code does across every session, while a poorly scoped one fills the context window with instructions the task never needed.

These articles review the skills and plugins worth installing, explain how skills load and why they fail, and follow how OpenAI, Anthropic and others are opening their coding agents to each other.

## All 5 articles

- [9 Essential Claude Skills for AI Engineers Building Production Agents + 1 Bonus Skill](https://www.maximem.ai/blog/claude-skills-for-engineers) — Updated 25 September 2026: Nine Claude Skills we run in production, plus one bonus, with the install command for each and what it saves you. Updated September 2026.
- [How To Use Jev In Your AI Agent: A Map Of Decision Seams](https://www.maximem.ai/blog/how-to-use-jev-in-your-ai-agent-a-map-of-decision-seams) — 2026-09-18: Jev cannot write a single word, which is the reason to care about it, so the question worth asking is never whether it should be your agent but which decisions inside your agent it should own.
- [Best Claude Code Skills in 2026: 12 New Skills and What Changed](https://www.maximem.ai/blog/claude-skills-for-engineers-h2-2026) — August 10, 2026: Important Claude Code skills shipped since February 2026, what each replaces, install commands, and the security problem that came with the marketplace.
- [Why OpenAI shipped an Official Plugin for Claude Code](https://www.maximem.ai/blog/openai-plugin-for-claude-code) — July 13, 2026: OpenAI ships Codex plugin for ClaudeCode harness
- [Why Skills Are The New Microservices](https://www.maximem.ai/blog/skills-new-microservices) — May 16, 2026: Skills are how modular AI agents scale. Discover why skills replace monolithic prompts, how to architect composable agents, and the context management patterns that make them work at scale.

Start here: [Agent skills research](https://www.maximem.ai/research/agent-skills) · [Memory vs agent skills](https://www.maximem.ai/memory-vs-agent-skills) · [Agent skills (glossary)](https://www.maximem.ai/glossary/agent-skills)

Other topics: [AI Agent Memory](https://www.maximem.ai/blog/topic/agent-memory) · [Context Engineering](https://www.maximem.ai/blog/topic/context-engineering) · [RAG & Retrieval](https://www.maximem.ai/blog/topic/rag) · [MCP & Agent Protocols](https://www.maximem.ai/blog/topic/mcp) · [Agent Frameworks](https://www.maximem.ai/blog/topic/frameworks) · [Agent Evals & Observability](https://www.maximem.ai/blog/topic/evals) · [Voice Agents](https://www.maximem.ai/blog/topic/voice-agents) · [LLM Cost & Production](https://www.maximem.ai/blog/topic/production) · [Research & Product Updates](https://www.maximem.ai/blog/topic/research)

---

Source: [https://www.maximem.ai/blog/topic/coding-agents](https://www.maximem.ai/blog/topic/coding-agents)