Claude Code Plugins High Level

To skim through all available tools provided by Claude Code: Claude Code Plugins — High‑Level Reference This is a high‑level, memory‑oriented overview of all official plugins in anthropics/claude-plugins-official / plugins. For each plugin: what it’s for when to reach for it 1‑line prompt example to activate it Core Agent & Skill Development agent-sdk-dev Purpose: SDK … Continue reading Claude Code Plugins High Level

Know Your Plugins

knowing what plugins you have is important so you know when to switch them on for various work. Claude Plugin Operational Reference This document is a tool‑level, memory‑optimized reference for two high‑impact Claude plugins: Enterprise‑Capabilities (strategy & architecture reasoning) Playwright (browser automation & end‑to‑end testing) It is designed to answer one question quickly: “What can … Continue reading Know Your Plugins

Plugins, Skills and MCP Servers/Connectors

I’ve been digging into how tools actually work in modern AI coding setups (like Claude Code), and here’s the simplest way to understand the landscape: 1. Plugins vs skills.md skills.md is just context — docs, conventions, instructions Plugins are capabilities — they can execute code, call APIs, and interact with real systems skills.md = “what … Continue reading Plugins, Skills and MCP Servers/Connectors

From Claude Code’s Harnessing to Index Construction Harnessing

Claude Codes is not a simple LLM, Here is a breakdown of every piece: Configuration (active) settings.json — your permissions, allowed tools, MCP server config, hooks settings.local.json — machine-local overrides (not committed) settings.json.backup / .OPTIMIZED — snapshots from past config changes CLAUDE.md — your global instructions injected into every conversation .credentials.json — your Anthropic API … Continue reading From Claude Code’s Harnessing to Index Construction Harnessing

You’re Not Calm—You’re Capable

The idea that “emotional control” is the key to staying calm under pressure sounds appealing—but it’s often misunderstood. What people call emotional control is, in many cases, actually a byproduct of something deeper: confidence in one’s ability to handle the situation. When you truly believe you can solve a problem, your mind doesn’t panic. Think … Continue reading You’re Not Calm—You’re Capable

How Smart Engineers Solve the Knowledge Sharing Problem in Large Enterprises

In large enterprises, knowledge sharing is one of the most difficult problems engineering teams face. Even when documentation and FAQs exist, new hires and less experienced users often struggle to navigate them effectively. Systems are complex, context is fragmented, and information is spread across multiple tools. As a result, people naturally turn to chat-based interfaces … Continue reading How Smart Engineers Solve the Knowledge Sharing Problem in Large Enterprises

Tips of Using Claude Code

Prompt Structure A well-structured prompt dramatically improves output quality. Use this ordering as a template: Role + high-level task (1–2 sentences) — Establish who Claude is and what it’s doing Dynamic / retrieved content — Paste in the data, documents, or context Claude needs Detailed task instructions — Specific rules, constraints, and goals Examples / … Continue reading Tips of Using Claude Code

Claude Code Leaked, Learn from the Best 06

How Claude Code Prevents Attacks? Think of it as five concentric walls, each catching something the previous one missed. --- Wall 1: The Blocklist (Fastest, Dumbest) utils/permissions/dangerousPatterns.ts has a hardcoded set called DANGEROUS_BASH_PATTERNS: python, node, deno, ruby, perl, php, lua, npx bash, sh, zsh, fish, ssh eval, exec, env, xargs, sudo Before any bash tool … Continue reading Claude Code Leaked, Learn from the Best 06