Deep_Dives

Short how-to guidelines and long-form deep dives. High information density, system-architecture breakdowns, and hard numbers.

[ENTRIES: 3]

Claude2026.06.30

Pick the right Claude tier for agent workflows

Opus 4.8 orchestrates, Haiku 4.5 does the parallel grunt work, Sonnet 4.6 is the default in between. Choose by the job and the token bill, not the benchmark.

claudeopussonnethaikupricingagentsmodel-selection

Claude2026.06.30

Context engineering beats a bigger context window

Claude Code runs up to a 1M-token window on flagship models, but a bigger window doesn't fix a cluttered one — every turn replays the whole history and quality drops before the cap.

claude-codecontext-windowcontext-engineeringtokenssubagents

Claude2026.06.30

Why agents ignore your CLAUDE.md

A bloated CLAUDE.md gets filtered out as noise. Keep it to universal instructions and move everything else behind progressive disclosure.

claude-codeclaude-mdcontext-engineeringagents-mdprogressive-disclosure