{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/use-progressive-disclosure-for-agent-instructions",
  "id": "MHC-D-RESEARCH-0707",
  "version": "0.1.0",
  "title": "Use progressive disclosure for agent instructions",
  "summary": "Do not make every future task pay the context cost of every past instruction.",
  "kind": "principle",
  "body": "Keep the always-loaded layer small: purpose, trigger cues and essential constraints. Put task procedures in an invoked skill or workflow, and supporting references behind links or files that can be opened when needed. Design names and descriptions so the agent can discover the right material without preloading it all.",
  "limits": [
    "Deferred context is useless if triggers are vague or search is weak; critical safety rules may need to remain always visible."
  ],
  "topics": [
    "union-ai-context-memory-skills"
  ],
  "intents": [],
  "source_ids": [
    "RS-1ED947350C040106"
  ],
  "evidence": [
    {
      "claim": "Anthropic describes progressive disclosure as letting agents discover relevant context incrementally instead of loading all available material up front.",
      "source_id": "RS-1ED947350C040106",
      "role": "supports",
      "note": "Progressive retrieval depends on discoverability and can be slower than up-front loading.",
      "locator": "Agentic search and progressive disclosure"
    }
  ],
  "use_when": [
    "A reusable agent has many procedures, references and edge cases."
  ],
  "avoid_when": [
    "Deferred context is useless if triggers are vague or search is weak; critical safety rules may need to remain always visible."
  ],
  "example": "A GitHub agent sees one short rule for release work; the detailed release checklist and rollback references load only when a release task is detected.",
  "check": "Removing an unrelated skill's full text from a normal task does not reduce success.",
  "sources": [
    {
      "id": "RS-1ED947350C040106",
      "title": "Effective context engineering for AI agents",
      "url": "https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0707",
      "to": "MHC-D-RESEARCH-0708",
      "type": "useful_with",
      "url": "/knowledge/turn-a-recurring-ai-workflow-into-a-skill-only-when-the-trigger-is-clear"
    }
  ],
  "collections": [
    {
      "id": "RC-74B3DD1F3F9BDCB4",
      "title": "Give AI the right context, memory and reusable skills",
      "url": "/collections/give-ai-the-right-context-memory-and-reusable-skills"
    }
  ]
}