LLM tooling — 3 Technical Articles

Apr 15, 2026 · Operations

Boost Your Development Workflow with Claude Code: 10 Must‑Know Custom Commands

This article explains how Claude Code custom commands eliminate repetitive prompt typing and prompt drift by storing reusable markdown prompts in a version‑controlled .claude/commands directory, then demonstrates ten practical commands—ranging from environment checks to automated PR generation—applied to a real FastAPI ML inference service.

AI workflowClaude CodeCustom Commands

0 likes · 31 min read

Boost Your Development Workflow with Claude Code: 10 Must‑Know Custom Commands

Top Architecture Tech Stack

Apr 7, 2026 · Industry Insights

Why Claude Code’s Agent Shell Is Losing Its Mystery and What It Means for AI Tooling

A recent npm packaging mistake exposed Claude Code’s TypeScript source, prompting a rapid community rewrite that reveals the agent control layer is increasingly replicable, shifting the real competitive edge to model inference, prompt engineering, and ecosystem robustness in AI programming tools.

AI agentsClaude CodeLLM tooling

0 likes · 13 min read

Why Claude Code’s Agent Shell Is Losing Its Mystery and What It Means for AI Tooling

PaperAgent

Jan 8, 2026 · Artificial Intelligence

How Cursor’s Dynamic Context Cuts Agent Token Use by 47%

Cursor’s new dynamic context feature lets its coding agents treat long tool outputs as files and selectively load only needed data, reducing total token consumption by 46.9% while improving response quality through techniques like file‑based tool responses, conversation‑history summarization, Agent Skills standards, efficient MCP tool loading, and treating terminal sessions as files.

AI agentsCursorLLM tooling

0 likes · 8 min read

How Cursor’s Dynamic Context Cuts Agent Token Use by 47%