msd-core/capabilities/mempalace/capability.json

{
  "id": "mempalace",
  "role": "feature",
  "version": "1.7.0",
  "title": "MemPalace memory",
  "description": "Cross-session, cross-project memory: deliberate recall before discuss/plan and verbatim capture + temporal-KG sync at phase boundaries, via the MemPalace MCP server and CLI.",
  "tier": "full",
  "requires": [],
  "engines": {
    "gsd": ">=1.6.0"
  },
  "runtimeCompat": {
    "supported": [
      "*"
    ],
    "unsupported": []
  },
  "skills": [
    "mempalace-recall",
    "mempalace-capture"
  ],
  "agents": [
    "gsd-mempalace-curator"
  ],
  "hooks": [],
  "config": {
    "mempalace.enabled": {
      "type": "boolean",
      "default": false,
      "description": "Master toggle for the MemPalace memory capability."
    },
    "mempalace.memory_mode": {
      "type": "enum",
      "values": [
        "augment",
        "kg_backend",
        "replace"
      ],
      "default": "augment",
      "description": "How MemPalace relates to GSD native memory during recall/capture. 'augment' (default): the palace is an additive layer alongside .planning/graphs/ — native memory stays authoritative. 'kg_backend': knowledge-graph queries resolve against the palace's temporal KG as the primary source, with .planning/graphs/ as fallback. 'replace': recall resolves through the palace as the source of truth, native memory as fallback. Every mode stays onError:skip and default-resilient — an unreachable palace degrades to native memory, and GSD keeps writing .planning/graphs/ so no memory is lost. Cross-mode migration of existing .planning/graphs/ into the palace is a separate, not-yet-implemented concern."
    },
    "mempalace.wing": {
      "type": "string",
      "default": "",
      "description": "Palace wing name; empty derives from project_code / project dir."
    },
    "mempalace.recall_on_discuss": {
      "type": "boolean",
      "default": true,
      "description": "Inject wake-up + search recall at discuss:pre."
    },
    "mempalace.recall_on_plan": {
      "type": "boolean",
      "default": true,
      "description": "Produce MEMORY-RECALL.md at plan:pre."
    },
    "mempalace.capture_artifacts": {
      "type": "boolean",
      "default": true,
      "description": "File CONTEXT/PLAN/SUMMARY and learnings into the palace at phase boundaries."
    },
    "mempalace.mirror_kg": {
      "type": "boolean",
      "default": true,
      "description": "Mirror decisions/learnings into MemPalace's temporal knowledge graph."
    },
    "mempalace.cross_project_tunnels": {
      "type": "boolean",
      "default": false,
      "description": "Propose/create cross-wing tunnels at ship:post."
    },
    "mempalace.diary_journal": {
      "type": "boolean",
      "default": true,
      "description": "Write a per-agent diary entry at ship:post."
    },
    "mempalace.auto_capture_hooks": {
      "type": "boolean",
      "default": false,
      "description": "Reserved / not yet implemented: will install MemPalace's native stop/precompact Claude Code hooks for passive mid-session capture (the capability's hooks array is currently empty)."
    }
  },
  "steps": [
    {
      "point": "discuss:post",
      "ref": {
        "skill": "mempalace-capture"
      },
      "produces": [],
      "consumes": [
        "CONTEXT.md"
      ],
      "when": "mempalace.enabled",
      "onError": "skip"
    },
    {
      "point": "plan:pre",
      "ref": {
        "skill": "mempalace-recall"
      },
      "produces": [
        "MEMORY-RECALL.md"
      ],
      "consumes": [
        "CONTEXT.md"
      ],
      "when": "mempalace.enabled",
      "onError": "skip"
    },
    {
      "point": "plan:post",
      "ref": {
        "skill": "mempalace-capture"
      },
      "produces": [],
      "consumes": [
        "PLAN.md"
      ],
      "when": "mempalace.enabled",
      "onError": "skip"
    },
    {
      "point": "verify:post",
      "ref": {
        "skill": "mempalace-capture"
      },
      "produces": [],
      "consumes": [
        "SUMMARY.md"
      ],
      "when": "mempalace.enabled",
      "onError": "skip"
    },
    {
      "point": "ship:post",
      "ref": {
        "agent": "gsd-mempalace-curator"
      },
      "produces": [],
      "consumes": [
        "UAT.md"
      ],
      "when": "mempalace.enabled",
      "onError": "skip"
    }
  ],
  "contributions": [
    {
      "point": "discuss:pre",
      "into": "orchestrator",
      "fragment": {
        "path": "fragments/recall-discuss.md"
      },
      "produces": [],
      "consumes": [],
      "when": "mempalace.enabled",
      "onError": "skip"
    },
    {
      "point": "execute:wave:post",
      "into": "verifier",
      "fragment": {
        "path": "fragments/capture-problems.md"
      },
      "produces": [],
      "consumes": [],
      "when": "mempalace.enabled",
      "onError": "skip"
    }
  ],
  "gates": []
}