Tools Howto 01
Compaction: when to summarize an agent's history — and when it backfires
Anthropic's compaction API summarizes an agent's history when it hits a token threshold. How it works, the billing pass you don't see, and when it backfires.
Category Independent editorial
Tools & how-to.
3 posts in this category.
3
2
12min avg
About
Concrete how-to guides for working with LLM APIs and tooling -- enabling prompt caching the right way, instrumenting cost telemetry, picking a model for a specific workload class. Each guide includes runnable code or commands, the exact vendor page that documents the API surface, and a date stamp that lets the reader judge how fresh the recipe is. We do not publish a how-to until it has been run against a live API at least once. The category opens empty in Phase D. The first guides will follow once the analysis catalogue covers the conceptual ground a how-to builds on.
§ Filter by category
Category
Showing 3 of 3 posts — page 1 of 1
Tools Howto 02
Context editing: cut agent token bills ~84% by clearing stale tool results
Anthropic's context editing clears stale tool results from an agent's window, cutting token use up to 84%. How it works, the config, and the prompt-cache catch.
Tools Howto 03
Caveman mode for Claude Code: the math behind the 65% headline
Caveman mode strips filler from Claude's output. The 65% headline is real for output tokens. Here's what it actually saves on your monthly bill.