Your Agent's Context Pack Is a Snapshot. Snapshots Rot.
You hand the agent a map of the codebase. By the time it acts on it, the map is wrong. The fix isn't a bigger context window — it's cheap freshness checks.
Read articleTopic
You hand the agent a map of the codebase. By the time it acts on it, the map is wrong. The fix isn't a bigger context window — it's cheap freshness checks.
Read articleThe most useful guardrail I've added to my agentic workflow isn't a better model or a longer context window. It's a hard rule: three files per task. Anything bigger gets split, even when the agent insists it can handle it.
Read articleInstruction files used to be docs humans skimmed. Now they are runtime input an agent trusts literally. The rot that didn't matter in a README will derail your next agent run.
Read articleThe agent from yesterday looked productive. The agent from today has forgotten every decision you made. Here's the cheap handoff that stops the reset.
Read articleA 4-hour agent conversation starts re-suggesting things it already tried. The fix isn't more prompting. It's a checkpoint and a clean session.
Read articleThe real cost of moving between Cursor, Cline, and Claude Code isn't the editor. It's re-explaining the same repo to each one from scratch. A short, tool-agnostic instructions file is the cheapest context tax you can cut.
Read articleDumping every file into the prompt doesn't give the agent more signal — it buries the one file it actually needs. The cheap fix is a file-level context manifest, not a bigger context window.
Read articleMost MCP servers load everything eagerly, dump huge schemas into the system prompt, and make the agent pay for tools it will never call. The fix is boring: lazy, narrow, and spec-driven.
Read article