Context Compression

When your agent sessions blow past context limits or you're working with multi-million token codebases, this breaks down three compression approaches with real tradeoffs. The key insight is optimizing for tokens per task, not tokens per request, because aggressive compression that loses file paths or error messages costs more in re-fetching than it saves. Anchored iterative summarization with structured sections (intent, files modified, decisions, next steps) outperforms naive approaches by forcing the summarizer to populate explicit categories. The weakest link across all methods is artifact trail integrity, scoring 2.2-2.5 out of 5.0, so expect to build separate file tracking if your agent needs reliable modification history. Includes probe-based evaluation strategies and a three-phase workflow for compressing large codebases into executable specs.

Install to Claude Code

npx -y skills add sickn33/antigravity-awesome-skills --skill context-compression --agent claude-code