Claude Code Subagents: When and How to Use Them
Learn when Claude Code subagents help and when they waste tokens: built-in agents, custom subagent files, and orchestration patterns for parallel work.
35 stories
Learn when Claude Code subagents help and when they waste tokens: built-in agents, custom subagent files, and orchestration patterns for parallel work.
Learn how Cursor skills work in 2026: set up .cursor/skills with SKILL.md, decide skills vs rules, install from a registry, and fix skills that won't load.
Learn Claude Code hooks with copy-paste examples: block dangerous commands, format on save, gate stops on passing tests, plus exit codes and debugging.
MCP security guide for developers: tool poisoning, prompt injection, malicious servers, and the practical steps to lock down your MCP setup.
AGENTS.md vs CLAUDE.md: which context file should your repo use in 2026? Compare tool support, symlink tricks, and migration paths in both directions.
Are Claude skills safe to install? How malicious skills use prompt injection and exfiltration, plus a 10-minute audit checklist to vet any skill.
Claude Code skills vs commands vs subagents, explained: how each mechanism works, what it costs in context, and when to reach for hooks instead.
Too many MCP tools can burn tens of thousands of tokens before your first prompt. Audit your MCP token usage and fix context bloat with four steps.
Learn how to build an MCP server in TypeScript: define tools with Zod schemas, add resources and prompts, test with MCP Inspector, and deploy over Streamable HTTP.
MCP transports compared: stdio for local servers, Streamable HTTP for remote, and what the SSE deprecation means — with a decision tree and migration steps.
Set up a private skill registry for your team's internal agent skills: compare git, self-hosted, and hosted options with SSO, roles, and audit logs.
Learn how to share Claude skills with your team: git repos, plugin marketplaces, and hosted registries, plus versioning, rollout, and usage analytics.
Build a private Claude Code plugin marketplace with marketplace.json in a git repo: setup, authentication, versioning, and a hosted alternative.
Stop MCP config drift. Learn how to share MCP servers across your team with version-controlled .mcp.json, safe secrets, and server allowlists.
Debug an MCP server fast with MCP Inspector: launch it against stdio and remote servers, test tools interactively, read MCP logs, and catch failures in CI.
Antigravity 2.0 is Google's agent-building platform — one agent harness you reach through a desktop app, the agy CLI, an SDK, and a single Managed Agents API. This is a builder-level walkthrough of its capabilities and the path from a prototype agent to one you'd trust in production.
We've put together a guide on how to create, import, and use Agent Skills in TRAE.
Showing 35 of 35 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts