Memory - Read & Access Operations

Unified read-side memory skill with subcommands for searching, loading, syncing, history, and visualization.

Cross-session read strategy (Opus 4.7 / CC 2.1.111+): Opus 4.7 reads filesystem memory more reliably than 4.6. 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 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)

Usage

/ork:memory search <query>  # Search knowledge graph
/ork:memory load             # Load context at session start
/ork:memory history          # View decision timeline
/ork:memory viz              # Visualize knowledge graph
/ork:memory status           # Show memory system health

---

CRITICAL: Use AskUserQuestion When No Subcommand

If invoked without a subcommand, ask the user what they want:

AskUserQuestion(
  questions=[{
    "question": "What memory operation do you need?",
    "header": "Operation",
    "options": [
      {"label": "search", "description": "Search decisions and patterns in knowledge graph", "preview": "```\nSearch Knowledge Graph\n──────────────────────\n  query ──▶ mcp__memory ──▶ results\n\n  Flags:\n  --category  Filter by type\n  --agent     Scope to agent\n  --limit N   Max results\n  --global    Cross-project\n```"},
      {"label": "load", "description": "Load relevant context for this session", "preview": "```\nLoad Session Context\n────────────────────\n  Auto-detect project ──▶\n  ┌────────────────────┐\n  │ Recent decisions   │\n  │ Active patterns    │\n  │ Project entities   │\n  └────────────────────┘\n  Flags: --project, --global\n```"},
      {"label": "history", "description": "Decision timeline + knowledge-graph viz (--mermaid)", "preview": "```\nDecision Timeline & Graph Viz\n─────────────────────────────\n  ┌──── Feb 28 ────────────┐\n  │ Used Postgres over Mongo│\n  ├──── Feb 27 ────────────┤\n  │ Adopted MVC pattern     │\n  └────────────────────────┘\n  --mermaid ──▶ [Project]──uses──▶[Postgres]\n```"},
      {"label": "status", "description": "Check memory system health", "preview": "```\nMemory Health Check\n───────────────────\n  ┌─────────────────────┐\n  │ MCP server    ✓/✗   │\n  │ Entity count  N     │\n  │ Relation count N    │\n  │ Last write    date  │\n  │ Graph size    N KB  │\n  └─────────────────────┘\n```"}
    ],
    "multiSelect": false
  }]
)

---

Subcommands

Load details: Read("${CLAUDE_SKILL_DIR}/references/memory-commands.md") for full usage, flags, output formats, and context-aware result limits for each subcommand.

---

Scheduled Sweeps (cron)

Nightly KG staleness report

Cron job in .github/workflows/memory-staleness.yml runs nightly at 04:00 UTC. Calls scripts/staleness_cron.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.

python3 plugins/ork/skills/memory/scripts/staleness_cron.py docs/reports/ \
    --threshold-days 30 --limit 50

Auto-skip conditions (all exit 0, all WARN-logged):

Report contents:

• Total / stale / fresh entity counts
• Top N stale entries sorted by staleness (no-timestamp first, then oldest → newest)
• Each row: name, entityType, age in days, observations count
• Suggested actions per age bucket (>90d review, >180d archive candidate)

Treats entities with no parsable timestamp as stale — operator intervention is the right outcome (backfill last_read observation OR prune).

Pure helpers (parse_iso_timestamp, latest_observation_timestamp, is_stale, build_report_payload, render_markdown) live in sibling staleness_lib.py for unit-testability.

Mirrors Yonatan-HQ/hq-ext-plugin#194 (audio_podcast) and orchestkit#1886 (post-synth podcast) + #1887 (memory writeback) pattern. Unblocked by Yonatan-HQ/core#993 (yg-mcp-core 0.3.0).

---

Workflow

1. Parse Subcommand

Extract first argument as subcommand
If no subcommand -> AskUserQuestion
Validate subcommand is one of: search, load, history, viz, status
Parse remaining flags
Check for --agent <agent-id> flag → agent_id: "ork:{agent-id}"

2. Execute Subcommand

Route to appropriate handler based on subcommand.

3. Report Results

Format output appropriate to the operation.

---

Rules Quick Reference

---

Session Resume

Load details: Read("${CLAUDE_SKILL_DIR}/references/session-resume-patterns.md") for CC 2.1.31 resume hints, context capture before ending, and resume workflows for PRs, issues, and implementations.

---

Related Skills

• ork:remember - Store decisions and patterns (write-side)

---

Error Handling

• If graph empty for viz: Show helpful message about using /ork:remember
• If subcommand invalid: Show usage help
• If memory files corrupt: Report and offer repair
• If search query empty: Show recent entities instead
• If no search results: Suggest alternatives