Claude,
explained simply.
Plain-English guides to Claude's newest features, the hidden tools on Anthropic's GitHub, and the agent harness patterns — agents, subagents, hooks, skills, MCP — that make AI engineers faster every day.
The Claude library
Guides
ECC: the harness that won Anthropic's hackathon
How 286 skills and 68 subagents work as a pipeline — and the stealable patterns (review loops + memory vault) behind 260K GitHub stars.
Opus 5.5 in plain English
Anthropic's new flagship model: 20% cheaper tokens, 30%+ faster output, a 1M-token context window — and the benchmark scores that back it up.
5 official Claude plugins you didn't know existed
Anthropic's own marketplace plugins: deep security scans, codebase setup plans, CLAUDE.md care, the agent SDK kit, and real C++ code intelligence.
Skills vs subagents vs hooks
The three words everyone mixes up: reusable playbooks, fresh-context specialists, automatic tripwires — and which one you actually need.
Spotify's shunt plugin, explained
How Spotify cut Claude Code token usage by a reported 90%: bulk file reads and boilerplate rerouted to a cheap worker model — hooks, bash scripts, and skills doing the triage, with honest limits.
The security-guidance plugin, explained
Anthropic's official security plugin for Claude Code: instant pattern warnings on every edit, an Opus 4.7 diff review each turn, and an agentic data-flow review on commit — plus honest limits.
The code-modernization plugin, explained
Anthropic's official legacy-modernization plugin for Claude Code: an enforced assess → approve → build → prove sequence, five specialist agents, three build methods, and a byte-level proof that the new code behaves like the old.
What happens when you hit enter in Claude
Your prompt becomes one HTTPS request with stream: true. Time to first token, SSE (not NDJSON), the six-event state machine your client stitches into words — and why the “Cogitating…” spinner is honest theater.
7 hidden Claude Code settings that change everything
Buried in the settings files: the permission mode new sessions start in, hooks that guard your secrets, a custom status line, your default model, output styles, and auto-compact — with the exact JSON for each.
Anatomy of a .claude/ folder: 7 things inside
Every Claude Code project hides a .claude/ folder that quietly decides how Claude behaves: shared settings, private overrides, skills, subagents, slash commands, memory, and hooks — with the exact file templates.
Ship faster
with Claude.
Every guide explains one Claude feature or harness pattern in plain English, shows it working on a real example, and hands you the copy-pasteable setup — so you can use it in your daily work the same day.