Update to CompText Evidence

{
  "description": "Use when the user explicitly asks whether verification evidence is fresh enough to support an AI completion claim after workspace mutations.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 290
    }
  ],
  "name": "verify-freshness",
  "skill_md_contents": "---\nname: verify-freshness\ndescription: Use when the user explicitly asks whether verification evidence is fresh enough to support an AI completion claim after workspace mutations.\n---\n\n# Verify evidence freshness\n\nFor bundled fixtures, run exactly:\n`node \"${CODEX_HOME:-$HOME/.codex}/plugins/cache/comptext-marketplace/comptext-evidence/0.1.0/scripts/freshness-gate.mjs\" \"${CODEX_HOME:-$HOME/.codex}/plugins/cache/comptext-marketplace/comptext-evidence/0.1.0/fixtures/<fixture>.jsonl\"`\nUse only `stale-after-mutation`, `fresh-after-verification`, or `failed-mutation-does-not-stale`; do not inspect bundled source unless the command fails.\n\n- For user traces, require bounded content-free JSONL containing only sequence, event type, and success state.\n- A successful mutation makes prior verification stale; a failed mutation does not.\n- Only successful verification after the latest successful mutation clears pending state; assertion never clears it.\n- Do not persist prompts, source text, raw commands/output, credentials, or environment values in traces.\n- Return trace digest, mutation/verification sequence, pending state, completion verdict, and reason.\n- For Riqor comparisons, report compatibility or divergence; never claim this implementation is Riqor.\n"
}