Public skill
memory-engineering
Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a CLAUDE.md or memory directory actually holds, deciding what to keep and what to expire, or when a memory store keeps growing and nobody has said what leaves it. Prices the write path, picks which cost to pay, classifies records as facts / skills / logs, and refuses a design that has no forgetting policy.
Package contents
Manifest
Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a CLAUDE.md or memory directory actually holds, deciding what to keep and what to expire, or when a memory store keeps growing and nobody has said what leaves it. Prices the write path, picks which cost to pay, classifies records as facts / skills / logs, and refuses a design that has no forgetting policy.
97e249d85368bb4b22de7368a9835f7bc8e337a18b8eda0b16944ea9b6c59d8c- SKILL.md6,720 bytes
- assets/forgetting_policy_template.md4,511 bytes
- assets/memory_design_spec.example.json2,098 bytes
- assets/memory_engineer_worksheet.md5,439 bytes
- references/forgetting_policy_design.md8,877 bytes
- references/memory_control_and_governance.md7,544 bytes
- references/memory_cost_canon.md7,030 bytes
- references/what_to_keep.md7,786 bytes
- scripts/forgetting_policy_linter.py15,509 bytes
- scripts/memory_architecture_picker.py15,780 bytes
- scripts/memory_cost_profiler.py13,675 bytes
- scripts/memory_density_auditor.py26,561 bytes
Release history