{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-30T18:53:33.881Z",
  "record_id": "VXI-EXT-ICE10-CLAUDE-CODE-SKILL-INVOCATION-AUTHORITY-01-v1",
  "record_kind": "external_reference",
  "title": "User command visibility versus autonomous invocation authority",
  "system": "Anthropic",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Does user-invocable false prevent Claude from invoking a sensitive skill?",
  "near_questions": [
    "Does hiding a Claude Code skill from users block model invocation?",
    "How do user-invocable and disable-model-invocation differ?",
    "Which Claude Code flag prevents automatic model use of a skill?",
    "Can slash-command visibility establish skill execution authority?"
  ],
  "supported_claims": [
    {
      "claim": "The guide distinguishes disable-model-invocation true, which prevents autonomous invocation, from user-invocable false, which removes user invocation while allowing Claude to invoke the skill.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "Do not confuse command visibility with prohibition of model invocation or downstream tool authority.",
    "Buyer implementation, live runtime enforcement, settled payment, verified deletion or certification are not established.",
    "No expanded capabilities or licences for existing INDEX executables."
  ],
  "public_summary": "The guide distinguishes disable-model-invocation true, which prevents autonomous invocation, from user-invocable false, which removes user invocation while allowing Claude to invoke the skill.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "Anthropic primary documentation: claude code skills",
    "source_url": "https://code.claude.com/docs/en/skills.md",
    "checked_on": "2026-10-30",
    "candidate_record_id": "VXI-EXT-ICE10-CLAUDE-CODE-SKILL-INVOCATION-AUTHORITY-01-v1",
    "candidate_record_sha256": "37ab21a5ce8ba220c7cec98e3248ac90e09ed44d44f1660dd4a3e2afba2f406b",
    "method": "Primary documentation reviewed for the published bounded statement.",
    "deployment_tested_by_varexis": false,
    "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research."
  },
  "answer_policy": {
    "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY",
    "bounded_answer": "The guide distinguishes disable-model-invocation true, which prevents autonomous invocation, from user-invocable false, which removes user invocation while allowing Claude to invoke the skill.",
    "required_buyer_context": "frontmatter; command visibility; desired invocation actor; separate tool permissions. Buyer deployment not inspected.",
    "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state."
  },
  "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.",
  "decision_profile": {
    "schema": "varexis-vendor-evidence-review/1",
    "review_status": "documentation_review_only",
    "applicability_status": "Primary rolling documentation captured 2026-10-30; runtime/version applicability must be checked before reliance. No buyer deployment was inspected.",
    "checked_on": "2026-10-30",
    "claim_to_check": "Does user-invocable false prevent Claude from invoking a sensitive skill?",
    "documented_statement": {
      "status": "documented",
      "statement": "The guide distinguishes disable-model-invocation true, which prevents autonomous invocation, from user-invocable false, which removes user invocation while allowing Claude to invoke the skill.",
      "source_ids": [
        "claude-code-skills-md"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "Does user-invocable false prevent Claude from invoking a sensitive skill? Do not confuse command visibility with prohibition of model invocation or downstream tool authority. User command visibility versus autonomous invocation authority. The decision turns on the documented operation and required evidence, not on a different vendor name. This is an operational review inference, not an observed deployment outcome.",
      "source_ids": [
        "claude-code-skills-md"
      ]
    },
    "buyer_evidence_required": [
      "frontmatter",
      "command visibility",
      "desired invocation actor",
      "separate tool permissions"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "Do not confuse command visibility with prohibition of model invocation or downstream tool authority."
    },
    "unknowns": "The buyer implementation, effective authority, source-data completeness and actual business outcomes were not inspected.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "No buyer deployment or transaction was observed."
    },
    "evidence_sources": [
      {
        "source_id": "claude-code-skills-md",
        "url": "https://code.claude.com/docs/en/skills.md",
        "final_url": "https://code.claude.com/docs/en/skills.md",
        "captured_at_utc": "2026-10-30T18:29:15.978177+00:00",
        "status": 200,
        "content_type": "text/markdown; charset=utf-8",
        "bytes": 118879,
        "sha256": "d2a5d07c0d1cef1d1edcf30f38f6b2712ff70ac050e3d50601cd3dadb42f9097",
        "title": "Anthropic primary documentation: claude code skills",
        "publisher": "Anthropic",
        "checked_on": "2026-10-30",
        "capture_status": 200,
        "claim_review_completed": true,
        "hash_basis": "SHA-256 of captured HTTP response-body bytes; not a signature or factual guarantee.",
        "version_context": "Rolling primary documentation captured 2026-10-30. The capture pins source bytes, not a provider runtime release; verify the installed version and configuration.",
        "rights_disposition": "Original bounded paraphrase with source attribution. Captured source body remains private; no source-body redistribution. Vendor documentation rights, code licences and marks are not transferred.",
        "reviewed_sections": [
          "If the YAML between the markers",
          "Control who invokes a skill",
          "Inject dynamic context",
          "How Claude Code handles the body of a synced skill"
        ]
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Documentation supports only the stated boundary. Existing licensed checkers analyse supported supplied declarations locally; they do not inspect provider accounts, verify live behaviour, enforce decisions or certify compliance.",
    "paid_value": {
      "decision_context": "Does user-invocable false prevent Claude from invoking a sensitive skill? Do not confuse command visibility with prohibition of model invocation or downstream tool authority.",
      "free": "Complete source review, questions, provenance and limitations; free to read and save locally.",
      "single_request": "Unavailable for this publication-only record; historical saved retrieval is unchanged.",
      "evidence_receipt": "Unavailable for this publication-only record; no paid retrieval entitlement is added.",
      "excluded": [
        "Fresh source research",
        "Native provider integration or schema support",
        "Live inspection or runtime enforcement",
        "Payment settlement or verified deletion",
        "Certification or expanded licences"
      ],
      "integrity": "Hashes identify content versions; they do not prove factual truth or provide a signature."
    },
    "revalidation": {
      "trigger": "Recheck current primary documentation and the applicable API, service, account and configuration before reliance. No ongoing monitoring is included.",
      "specific_watch": "Control who invokes a skill"
    },
    "buyer_relevance": "Does user-invocable false prevent Claude from invoking a sensitive skill? Do not confuse command visibility with prohibition of model invocation or downstream tool authority.",
    "refusal_conditions": [
      "Do not confuse command visibility with prohibition of model invocation or downstream tool authority.",
      "Do not infer deployment conformance, authority or successful outcomes from source documentation."
    ],
    "decision_context": {
      "operator": "Skill admission reviewer",
      "scenario": "Does user-invocable false prevent Claude from invoking a sensitive skill?",
      "consequence": "Do not confuse command visibility with prohibition of model invocation or downstream tool authority.",
      "confidence": "Primary documentation supports the narrow stated distinction; deployment conformance and purchase demand remain unestablished."
    },
    "novelty_review": {
      "candidate_id": "ICE10-A17",
      "disposition": "distinct_operational_decision",
      "nearest_record_id": "VXI-EXT-OWASP-AGENTIC-SKILLS-02-v1",
      "nearest_record_url": "/varexis-index/records/agent-skills-versus-mcp-security-scope.json",
      "nearest_record_sha256": "5beaf7612c4b900f27b52040915a5bfe3f587be2c142793782215ead7ed10147",
      "material_distinction": "User command visibility versus autonomous invocation authority. The decision turns on the documented operation and required evidence, not on a different vendor name.",
      "review_status": "PASS: source qualification plus independent reviewer challenge and resolved corrections"
    },
    "optional_selection": {
      "guide_id": null,
      "guide_url": null,
      "guide_manifest": "/varexis-index/decision-guides.json",
      "checker": {
        "product_id": "agent-tool-admission",
        "price_gbp_excluding_vat": 49,
        "purchase_url": "/index-access?route=agentic_pack_tool_admission_v1",
        "licence_scope": "Existing separate internal-use licence; subscriptions do not include the executable.",
        "benefit": "Optional local analysis of supported supplied declarations only; no native provider integration or verification is added."
      },
      "boundary": "The existing checker does not connect to this platform or execute these review worksheets. Use it only for its already-supported supplied declaration schema and separate licence."
    },
    "exact_access": {
      "endpoint": "/mcp/catalogue",
      "tool": "get_publication_record",
      "arguments": {
        "record_id": "VXI-EXT-ICE10-CLAUDE-CODE-SKILL-INVOCATION-AUTHORITY-01-v1"
      },
      "record_url": "/varexis-index/records/claude-code-skill-invocation-authority.json",
      "original_mcp_search": false,
      "paid_saved_retrieval": false
    }
  },
  "niche": {
    "niche_id": "ice10-governance",
    "label": "Agent Governance & Policy Boundaries",
    "classification_id": "governance",
    "classification_label": "Agent Governance & Policy Boundaries",
    "topic_id": "governance",
    "buyer_intent": "Does user-invocable false prevent Claude from invoking a sensitive skill? Do not confuse command visibility with prohibition of model invocation or downstream tool authority.",
    "comparison_role": "supplementary_discovery"
  },
  "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.",
  "service_route": {
    "request_guide": "/varexis-index/request.html",
    "request_workflow": "/varexis-index/request-workflow.json",
    "service_id": "single_request",
    "service_routes_url": "/varexis-index/service-routes.json",
    "payment_required": true,
    "availability_endpoint": "/api/index/capabilities",
    "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED",
    "checkout_url": "/index-access"
  },
  "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.",
  "human_page": "/varexis-index/catalog.html#claude-code-skill-invocation-authority",
  "machine_readable_record": "/varexis-index/records/claude-code-skill-invocation-authority.json"
}