Adopt

5 surfaces
Tools/Spec Introspection/reflect

reflect

[LLM-mediated] This tool returns a routing envelope, not computed results. For user-facing reflection, invoke the /upg-reflect skill instead of calling this tool directly. Reflect approach: path of arrival to "what should I be questioning?". Returns the Reflect record + invocation params in the family-resemblance envelope. The LLM consumes `mode` + `scope` + `signature_hint` and emits `{ prompts: [{ kind, question, target_entities? }] }`. `mode` is one of: `assumptions`, `alternatives`, `blind-spots`, `load-bearing`; omit for open reflection. `scope` accepts a region id, entity id, or `null` for whole-graph.

Spec Introspectionatomic (read-only)

Arguments

scopestringnulloptional

Optional. Region id, entity id, or null for whole-graph.

modestringoptional

Optional. One of: assumptions, alternatives, blind-spots, load-bearing. Omit for open reflection.

assumptionsalternativesblind-spotsload-bearing

Returns

JSON envelope: { approach_id, scope, generated_at, approach, params, prompts, execution_mode: "execution_v0_4_0" }

Examples

Live call against the Notion example graph.

Output

{
  "approach_id": "reflect",
  "scope": null,
  "generated_at": "2026-05-29T20:13:20.019Z",
  "approach": {
    "id": "reflect",
    "label": "Reflect",
    "description": "The path of arrival to \"what should I be questioning?\". Reflect engages an optional scope (region, entity, or `null` for the whole graph) and emits structured prompts a thinker should consider: assumptions to test, alternatives to weigh, blind-spots to surface, load-bearing claims to verify. Mode is optional; absence is open reflection. Cartographic sense: before approaching the coastline, you are asking which features of your chart you have not actually verified; the prompts mark the parts of the map that may be conjecture. Five Whys, Pre-mortem, Red Team, and Devil's Advocate are the named techniques inside this approach.",
    "question_answered": "what should I be questioning?",
    "signature_hint": "({ scope?: UPGRegionId | entity_id | null, mode?: 'assumptions' | 'alternatives' | 'blind-spots' | 'load-bearing' }) → { prompts: [{ kind, question, target_entities? }] }",
    "framework_id_examples": [
      "five-whys",
      "pre-mortem",
      "red-team",
      "devils-advocate",
      "second-order-thinking",
      "retrospective",
      "four-forces-of-progress",
      "assumption-canvas",
      "win-loss-analysis"
    ]
  },
  "params": {
    "scope": null,
    "mode": null
  },
  "prompts": [
… (truncated)

See Also