Loading...
Loading...
Automatic context summarization for long-running sessions. Use when context is approaching limits, summarizing completed work, preserving critical information, or managing token budgets.
npx skill4agent add adaptationio/skrillz context-compactorfrom scripts.compactor import ContextCompactor
compactor = ContextCompactor()
if compactor.should_compact(context, limit=100000):
compacted = compactor.compact(context)compacted = compactor.compact(context)
# Preserves: architectural decisions, bugs, current state
# Discards: stale tool outputs, redundant messages┌─────────────────────────────────────────────────────────────┐
│ PRESERVATION PRIORITY │
├─────────────────────────────────────────────────────────────┤
│ │
│ MUST PRESERVE (Never remove) │
│ ├─ Architectural decisions │
│ ├─ Unresolved bugs and blockers │
│ ├─ Current feature state │
│ ├─ Recent file changes (last 5) │
│ └─ Error patterns and solutions │
│ │
│ CAN SUMMARIZE (Compress to summary) │
│ ├─ Completed features (list of IDs) │
│ ├─ Resolved errors (brief mention) │
│ └─ Historical decisions (key points) │
│ │
│ CAN DISCARD (Remove entirely) │
│ ├─ Redundant tool outputs │
│ ├─ Stale search results │
│ ├─ Superseded messages │
│ └─ Verbose logging │
│ │
└─────────────────────────────────────────────────────────────┘| Context Type | Limit | Action |
|---|---|---|
| < 50% | Normal | No action |
| 50-75% | Warning | Prepare for compaction |
| 75-90% | Compact | Trigger compaction |
| > 90% | Critical | Aggressive compaction |
references/COMPACTION-STRATEGY.mdreferences/TOKEN-BUDGETS.mdscripts/compactor.pyscripts/importance_scorer.pyscripts/summarizer.pyscripts/token_estimator.py