Claude Code: Context Engineering Audit

An audit of Claude Code against Anthropic's context engineering guidelines found that redundant injection of preference data was wasting tokens and violating lightweight and automatic memory rules. The audit traced a ~60-line list of preferences being injected three times per session via overlapping hooks in the .claude/settings.json file, increasing the probability of model distraction. The fix is to move from manual dumps to a leaner, tool-driven workflow that keeps CLAUDE.md strictly for architectural invariants.

Claude Code: Context Engineering Audit Claude /en/tags/claude/ Code setup against Anthropic's latest context engineering guidelines to see if my "sophisticated" automation was actually just adding noise. The goal was simple: stop front-loading every session with a wall of text and start treating context like scoped variables in a function. The Context Engineering Checklist If you're optimizing a Claude Code workflow, these are the five pillars to measure against: Lightweight It should be for "gotchas" and non-obvious patterns, not a comprehensive repo wiki. CLAUDE.md : Progressive Disclosure: Pull in skills and references only when the task demands them. Model Trust: Strip out redundant guardrails that newer models already handle natively. Automatic Memory: Stop manually maintaining preference blocks in markdown; let the system surface them. Tool-Centric Design: Move instructions into tool schemas and parameters rather than prose-heavy system prompts. The Bottleneck: Redundant Injection I traced my SessionStart hooks to see exactly what was hitting the context window. I found a massive overlap in how my local "memory" layer was interacting with the agent. My .claude/settings.json was triggering a sequence of commands that essentially shouted the same information three times: gps preferences --write Bakes a markdown block into CLAUDE.md gps preferences --markdown Prints the same list to stdout gps prime Emits a session primer that overlaps both The result? A ~60-line list of preferences was being injected three times—once via the file read and twice via hook output—before I even typed a single prompt. This is a textbook violation of the "lightweight" and "automatic memory" rules. Real-World Impact When you over-engineer the system prompt or the CLAUDE.md file, you aren't just wasting tokens; you're increasing the probability of the model getting distracted by irrelevant constraints. The fix is to move away from "manual dumps" and toward a leaner, tool-driven AI workflow. Instead of telling the model how to behave in a 60-line list, define those constraints within the tools it uses or keep the CLAUDE.md strictly for architectural invariants that the model cannot possibly infer from the code. For anyone building a custom LLM agent deployment, the lesson is clear: if you can't justify why a piece of information needs to be in the initial context window for 100% of tasks, it doesn't belong in the session start. Next LLM Stack 2026: The Fragmented Pricing Gap → /en/threads/3749/