II.
Experiment JSON
Structured · liveexperiment:claude-code-strengths
Claude Code Strengths Verification json
Inspect the normalized record payload exactly as the atlas UI reads it.
{
"id": "experiment:claude-code-strengths",
"_kind": "Experiment",
"_file": "domain/testable-claims/experiments.yaml",
"_cluster": "domain",
"attributes": {
"displayName": "Claude Code Strengths Verification",
"description": "Manual review confirming Claude Code's documented strengths: auto-dream\nmemory consolidation and comprehensive hook surface (PreToolUse,\nPostToolUse, Stop, etc.).\n",
"status": "completed",
"result": "validated",
"startedAt": "2026-05-10",
"completedAt": "2026-05-10",
"evidence": "Reviewed atlas graph nodes for Claude Code:\n- memory-system:claude-code-auto-memory has autoExtraction=true,\n consolidation=auto-dream confirmed\n- agent-core-impl:claude-code.core@1.x fires 7 hook surfaces including\n pre-tool-use, post-tool-use, stop, user-prompt-submit, subagent-start,\n subagent-stop, pre-compact — all confirmed in graph\n- capability:runtime-hooks and capability:stop-hook both at level:full\nBoth claims validated.\n"
},
"outgoingEdges": [
{
"from": "experiment:claude-code-strengths",
"to": "claim:claude-code-has-auto-dream",
"kind": "tests_claim"
},
{
"from": "experiment:claude-code-strengths",
"to": "claim:claude-code-has-hooks",
"kind": "tests_claim"
}
],
"incomingEdges": []
}