# Posts tagged #best-practices
Long-Context Isn't the Answer
Kyle · March 23, 2026 · 7 min read · #agents #claudecode #best-practices #context-engineering
We tried Opus with 1M context for coding agents, and now we're switching back. It turns out it's not about the size of the context window - it's about the quality.
Skill Issue: Harness Engineering for Coding Agents
Kyle · March 12, 2026 · 23 min read · #agents #claudecode #best-practices
Harness engineering is the art and science of leveraging your coding agent's configuration points to improve output quality and increase task success rates.
Context-Efficient Backpressure for Coding Agents
Dex · December 9, 2025 · 5 min read · #agents #claudecode #best-practices #devex
Verbose test and build output wastes tokens and confuses agents. A simple wrapper script can dramatically improve agent performance.
Writing a good CLAUDE.md
Kyle · November 25, 2025 · 10 min read · #agents #claudecode #best-practices
CLAUDE.md is a high-leverage configuration point for Claude Code. Learning how to write a good CLAUDE.md (or AGENTS.md) is a key skill for agent-enabled software engineering.
Advanced Context Engineering for Coding Agents
Dex · August 29, 2025 · 20 min read · #agents #claudecode #best-practices
How do we get AI coding agents to solve hard problems in complex, brownfield codebases?
12 Factor Agents
Dex · April 3, 2025 · 32 min read · #agents #llm #ai #best-practices #architecture
The Original 12 Factor Agents Manifesto. What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?