context-compression

1# Context Compression Strategies
2 
3When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is tokens per task: total tokens consumed to complete a task, including re-fetching costs when compression loses critical information.
4 
5## When to Activate
6 
7Activate this skill when:
8- Agent sessions exceed context window limits
9- Codebases exceed context windows (5M+ token systems)
10- Designing conversation summarization strategies
11- Debugging cases where agents "forget" what files they modified
12- Building evaluation frameworks for compression quality
13- Creating durable handoff summaries that preserve decisions, files, risks, and next actions
14 
15Do not activate this skill for adjacent work owned by other skills:
16- General token-efficiency tactics such as masking, prefix caching, or partitioning: `context-optimization`.
17- Diagnosing why a long context is failing before choosing a mitigation: `context-degradation`.
18- Writing raw outputs, logs, or plans to files without summarizing them: `filesystem-context`.
19- Designing long-term semantic memory across sessions: `memory-systems`.
20- The model deciding when and where to rewrite its own context: `self-managed-context`. This skill still owns what the replacement text must preserve.
21 
22## Core Concepts
23…