<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Claude-Code on Coding Agent Guide</title><link>https://codingagentguide.com/tags/claude-code/</link><description>Practical guides for AI coding Agent tutorials and operations.</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://codingagentguide.com/tags/claude-code/index.xml" rel="self" type="application/rss+xml"/><item><title>Instruction File Scope Checks for Coding Agent Repos</title><link>https://codingagentguide.com/posts/instruction-file-scope-checks-for-coding-agent-repos/</link><pubDate>Wed, 10 Jun 2026 16:55:57 +0000</pubDate><guid>https://codingagentguide.com/posts/instruction-file-scope-checks-for-coding-agent-repos/</guid><description>A practical guide to auditing the scope, placement, and content of instruction files — AGENTS.md, .github/copilot-instructions.md, CLAUDE.md, and similar — so coding agents in your repo stay within intended boundaries.</description></item><item><title>How Agent Guides Fail Without Source Backing: A Field-Level Breakdown</title><link>https://codingagentguide.com/posts/source-backed-failure-modes-in-agent-guides/</link><pubDate>Wed, 10 Jun 2026 07:24:10 +0000</pubDate><guid>https://codingagentguide.com/posts/source-backed-failure-modes-in-agent-guides/</guid><description>Agent guides that lack source backing produce instructions agents cannot verify, leading to silent drift, broken CI, and unsafe automation decisions. This article maps the concrete failure modes, explains where guidance gaps originate in real instruction files and memory systems, and gives operators a practical workflow for diagnosing and hardening their own agent guides.</description></item><item><title>Memory Hygiene for Long-Running Coding Agents</title><link>https://codingagentguide.com/posts/memory-hygiene-for-long-running-coding-agents/</link><pubDate>Sat, 06 Jun 2026 09:31:50 +0000</pubDate><guid>https://codingagentguide.com/posts/memory-hygiene-for-long-running-coding-agents/</guid><description>Long-running coding agents accumulate stale context, conflicting instructions, and forgotten constraints. This guide explains how to structure memory files, rotate context windows, and verify that your agent is operating from current instructions — not residue from a past session.</description></item><item><title>Pack Repository Context So Coding Agents Understand Your Codebase</title><link>https://codingagentguide.com/posts/repository-context-packing-for-agent-tasks/</link><pubDate>Thu, 04 Jun 2026 01:26:29 +0000</pubDate><guid>https://codingagentguide.com/posts/repository-context-packing-for-agent-tasks/</guid><description>A practical guide to structuring AGENTS.md, CLAUDE.md, Copilot instructions, and git worktrees so coding agents receive accurate, scoped context for every task.</description></item><item><title>Keep Coding Agent Prompt Registries Consistent With Drift Checks</title><link>https://codingagentguide.com/posts/prompt-registry-drift-checks-for-coding-agents/</link><pubDate>Fri, 29 May 2026 03:30:59 +0000</pubDate><guid>https://codingagentguide.com/posts/prompt-registry-drift-checks-for-coding-agents/</guid><description>Coding agents read instruction files — AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, and memory files — to understand what tools, workflows, and conventions are available. When those files drift from the actual runtime environment, agents make confidently wrong decisions. This guide explains what prompt registry drift is, how it appears across popular agent runtimes, and how to detect and prevent it with CI-backed drift checks.</description></item></channel></rss>