Memory

Read-side companion to /ork:remember that lets you search, load, and visualize your knowledge graph without dumping everything into context. The subcommand pattern (search, load, history, viz, status) keeps operations focused. Particularly clever is the layered read strategy: hit the filesystem index first, check session handoff files second, only query the MCP graph when you need typed traversal. Includes a nightly cron job that flags stale entities older than 30 days, which is the kind of maintenance hook you'll actually appreciate six months in. If you're building on OrchestKit's memory system and need to pull context at session start or hunt down past decisions, this is the other half of the loop.

skills.sh installs: 755
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yonatangross/orchestkit --skill memory --agent claude-code

Installs into .claude/skills of the current project.

Files

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:

~/.claude/projects/<slug>/memory/MEMORY.md (durable index — load first, always)

.claude/chain/state.json + most recent NN-*.json handoff (session continuation)

MCP mcp__memory__search_nodes 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

SUBCOMMAND = "$ARGUMENTS[0]"  # First token: search, load, history, viz, status
QUERY = "$ARGUMENTS[1]"       # Second token onward: search query or flags
# $ARGUMENTS is the full string (CC 2.1.59 indexed access)