Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
yonatangross avatar

Memory

  • 703 installs
  • 213 repo stars
  • Updated August 4, 2026
  • yonatangross/orchestkit

memory is an OrchestKit Claude Code skill that performs unified read-side memory operations—knowledge graph search, session context loading, decision history, and Mermaid visualization—for developers who need past projec

About

memory is an OrchestKit skill (version 2.0.1) that exposes read-side memory operations through subcommands search, load, history, viz, and status. The skill queries a memory MCP server to recall past decisions, load relevant session context, and render project knowledge graphs as Mermaid diagrams. It complements /ork:remember for write-side persistence and requires Claude Code 2.1.148+ plus the memory MCP server. Developers reach for memory when an agent session needs prior architectural decisions, timeline history, or a visual map of accumulated project knowledge.

  • Unified read-side memory operations for Claude Code
  • 5 core subcommands: search, load, history, viz, status
  • Knowledge graph search and Mermaid visualization
  • Session context loading and decision timeline viewing
  • Complements write-side /ork:remember skill

Memory by the numbers

  • 703 all-time installs (skills.sh)
  • +1 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #1,424 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/yonatangross/orchestkit --skill memory

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs703
repo stars213
Security audit3 / 3 scanners passed
Last updatedAugust 4, 2026
Repositoryyonatangross/orchestkit

How do you recall past agent decisions from memory?

Instantly recall past decisions, load relevant context, and visualize their project knowledge graph without repeating work.

Who is it for?

Claude Code developers using OrchestKit who need to search, load, or visualize accumulated project memory across sessions.

Skip if: Greenfield projects without a memory MCP server configured or agents that only need ephemeral single-session context.

When should I use this skill?

The user searches past decisions, loads project context, views decision history, or asks to visualize the knowledge graph.

What you get

Retrieved decision context, session memory payload, decision timeline, and optional Mermaid knowledge graph visualization.

  • Session context payload
  • Mermaid knowledge graph
  • Decision timeline

By the numbers

  • Exposes 5 memory subcommands: search, load, history, viz, status
  • Skill version 2.0.1 requires Claude Code 2.1.148+

Files

SKILL.mdMarkdownGitHub ↗

Memory - Read & Access Operations

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

Cross-session read strategy (Opus 4.8 / CC 2.1.111+): Opus 4.8 reads filesystem memory more reliably than older tiers. 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"},
      {"label": "load", "description": "Load relevant context for this session"},
      {"label": "history", "description": "Decision timeline + knowledge-graph viz (--mermaid)"},
      {"label": "status", "description": "Check memory system health"}
    ],
    "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.

SubcommandPurpose
searchSearch past decisions, patterns, entities. Supports --category (maps to metadata.category), --limit, --agent (scopes by agent_id), --global filter flags
loadAuto-load relevant memories at session start. Supports --project, --global
historyDecision timeline with table, Mermaid, or JSON output. Supports --since, --mermaid
vizRender knowledge graph as Mermaid diagram. See also Read("${CLAUDE_SKILL_DIR}/references/mermaid-patterns.md")
statusMemory 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/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 ${CLAUDE_SKILL_DIR}/scripts/staleness_cron.py docs/reports/ \
    --threshold-days 30 --limit 50

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

Skip reasonTrigger
yg-mcp-core not importableyg-mcp-core>=0.3.0 not installed (orchestkit is public; yg-mcp-core lives on private pypi.yonyon.ai — HQ-only)
memory MCP unreachablememory MCP server down OR .mcp.json doesn't define memory

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

RuleImpactWhat It Covers
entity-extraction-patterns (load ${CLAUDE_SKILL_DIR}/rules/entity-extraction-patterns.md)HIGHEntity types, relation types, graph query semantics
deduplication-strategy (load ${CLAUDE_SKILL_DIR}/rules/deduplication-strategy.md)HIGHEdit-over-Write pattern, anchor-based insertion, verification

---

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

Related skills

FAQ

What subcommands does the memory skill support?

The OrchestKit memory skill supports search, load, history, viz, and status subcommands for read-side operations. Use viz to render Mermaid knowledge graphs and history to review past decision timelines.

What does memory require to run?

The memory skill requires Claude Code 2.1.148 or newer and a configured memory MCP server. Version 2.0.1 pairs with /ork:remember on the write side for full OrchestKit memory workflows.

Is Memory safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.