Topic archive
A practical guide for engineers who run coding agents on long sessions. Covers which memory and instruction files each major agent platform reads at startup, how to review them before a multi-step task, and how to run a quick smoke test that confirms the agent starts with the right context.
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.
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.
A practical guide to structuring AGENTS.md, CLAUDE.md, Copilot instructions, and git worktrees so coding agents receive accurate, scoped context for every task.