Agent skill · writing content · yonatangross
memory
Read-side memory: search past decisions, load context, timelines and graph views. Use when finding what memory holds. To store use remember; to clean up use dream.
Why this skill is useful
Provides specific commands and workflows for accessing and visualizing memory data that the AI wouldn't reliably generate on its own.
What it needs
About 3k tokens when loaded. Last updated 2026-08-06. 215 stars on the source repository.
What this skill does
Memory - Read & Access Operations Unified read-side memory skill with subcommands for searching, loading, syncing, history, and visualization. Cross-session read strategy (Opus 5.5 / CC 2.1.111+): Opus 5.5 reads filesystem memory reliably across sessions. When loading context at session start, prefer the layered read order: 1. ~/.claude/projects/<slug>/memory/MEMORY.md (durable index — load first, always) 2. .claude/chain/state.json + most recent NN-.json handoff (session continuation) 3. MCP mcpmemorysearchnodes for anything the filesystem index doesn't answer (typed graph traversal) Layer 1 is cheap (small index file), Layer 2 is scoped (session-specific), Layer 3 is selective (only when needed). Avoid dumping the full knowledge graph into context — use the index to narrow the search first. Argument Resolution Usage --- CRITICAL: Use AskUserQuestion When No Subcommand If invoked without a subcommand, ask the user what they want: --- Subcommands Load details: Read("references/memory-commands.md") for full usage, flags, output formats, and context-aware result limits for each subcommand. Subcommand Purpose ------------ --------- search Search past decisions, patterns, entities. Supports --category (maps to metadata.category), --limit, --agent (scopes by agentid), --global filter flags load Auto-load relevant memories at session start. Supports --project, --global history Decision timeline with table, Mermaid, or JSON output. Supports --since, --mermaid viz Render knowledge graph as Mermaid diagram. See also Read("references/mermaid-patterns.md") status Memory system health check --- Scheduled Sweeps (cron) Nightly KG staleness report Cron job in .github/workflows/memory-staleness.yml runs nightly at 04:00 UTC. Calls scripts/stalenesscron.py to scan ALL memory MCP entities, flag those whose latest observation timestamp is older than 30 days, and write a Markdown report to docs/reports/memory-staleness-YYYY-MM-DD.md. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills yonatangross/memory