context-management
WHAT: Retrieve, preserve, and measure only task-relevant agent context. USE FOR: evidence gaps in multi-agent work, durable context management, phase-boundary compaction, or local context/token projection reviews. DO NOT USE FOR: creating a competing specification/task store, hosted token counting, or reducing required safety and product behavior.
- License
- MIT
Pinned to revision 0bef895aff6a, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/context-management/SKILL.md
- skills/context-management/references/memory/assets/vault-templates.md
- skills/context-management/references/memory/references/memory.md
- skills/context-management/references/token-optimization/assets/context-projection.example.json
- skills/context-management/references/token-optimization/method-source.md
- skills/context-management/references/token-optimization/references/original-spec.md
- skills/context-management/references/token-optimization/scripts/measure_context.py
- skills/context-management/workflows/iterative-retrieval.md
- skills/context-management/workflows/memory.md
- skills/context-management/workflows/strategic-compact.md
- skills/context-management/workflows/token-optimization.md
Every link opens the file at its source, pinned to the revision this page describes.