aim-refresh

Imported from Hidden-History/ai-memory (_ai-memory/skills/aim-refresh/SKILL.md). Install upstream with npx skills add Hidden-History/ai-memory --skill aim-refresh. Copyright stays with the author.

Manually re-evaluates freshness for code-patterns memories. Reuses the freshness scan pipeline from SPEC-013 with optional scope filters.

Canonical Execution

Always run the real script through run-with-env.sh so the skill uses the installed ai-memory virtualenv and the standard local service defaults.

"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py

Examples

# Scan all code-patterns memories
"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py

# Limit to a specific project group_id
"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py my-project

# Topic filter (v2.1 — currently runs full scan with project filter)
"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py --topic "authentication"

Implementation

• Script: scripts/memory/refresh.py
• Interpreter: run-with-env.sh (imports memory.*, requires venv)
• Args: [project] (optional positional group_id filter), --topic (v2.1, no-op today)
• Output: tier table (Fresh / Aging / Stale / Expired / Unknown) + actionable count