iiRecord
Agentic AI Atlas · assimilation/harness/cursor
lib-process:meta--cursora5c.ai
II.
LibraryProcess JSON

lib-process:meta--cursor

Structured · live

assimilation/harness/cursor json

Inspect the normalized record payload exactly as the atlas UI reads it.

File · generated-library/processes.yamlCluster · generated-library
Record JSON
{
  "id": "lib-process:meta--cursor",
  "_kind": "LibraryProcess",
  "_file": "generated-library/processes.yaml",
  "_cluster": "generated-library",
  "attributes": {
    "displayName": "assimilation/harness/cursor",
    "description": "Orchestrate babysitter SDK integration into Cursor IDE/CLI.\n  Cursor is a VS Code fork with built-in AI capabilities. It has:\n  - A CLI (`cursor`) with headless agent mode (`cursor agent --print -p \"prompt\"`)\n  - Hooks system (1.7+): beforeSubmitPrompt, beforeShellExecution, beforeMCPExecution,\n    afterFileEdit, afterAgentResponse, stop — configured via .cursor/hooks.json\n  - NOTE: As of writing, hooks only fire in IDE mode, NOT in headless CLI mode.\n    The sessionStart hook fires in headless, but afterAgentResponse and stop do not.\n    This is a known limitation that may change — the research phase must verify current state.\n  - Config: .cursor/ directory, .cursorrules for rules\n  - MCP server support for tool access\n  - VS Code extension model (not a standalone plugin system)\n  - Already has minimal KNOWN_HARNESSES entry (HeadlessPrompt only, no callerEnvVars)\n  Key challenge: hooks don't work in headless CLI mode, so the continuation mechanism\n  is limited. The process must research the current state of Cursor hooks in CLI mode\n  and determine whether stop-hook, in-turn, or a hybrid approach is appropriate.",
    "libraryPath": "library/specializations/meta/assimilation/harness/cursor.js",
    "specialization": "meta"
  },
  "outgoingEdges": [
    {
      "from": "lib-process:meta--cursor",
      "to": "skill-area:ai-agent-development",
      "kind": "lib_requires_skill_area",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-process:meta--cursor",
      "to": "skill-area:orchestration-loop",
      "kind": "lib_requires_skill_area",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-process:meta--cursor",
      "to": "topic:developer-experience",
      "kind": "lib_covers_topic",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-process:meta--cursor",
      "to": "topic:integrations",
      "kind": "lib_covers_topic",
      "attributes": {
        "weight": 0.7
      }
    },
    {
      "from": "lib-process:meta--cursor",
      "to": "domain:software-engineering",
      "kind": "lib_applies_to_domain",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-process:meta--cursor",
      "to": "role:platform-engineer",
      "kind": "lib_involves_role",
      "attributes": {
        "weight": 1
      }
    },
    {
      "from": "lib-process:meta--cursor",
      "to": "specialization:meta",
      "kind": "lib_belongs_to_specialization",
      "attributes": {
        "weight": 0.9
      }
    }
  ],
  "incomingEdges": []
}