Update to XMemo

{
  "description": "Verify project or agent progress claims against an approved baseline, XMemo context, and current artifacts. Use to identify evidence gaps, drift, blockers, and the next action; distinguish claims from verified completion.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 413
    },
    {
      "relative_path": "assets/progress-audit-template.md",
      "size_in_bytes": 1045
    }
  ],
  "name": "xmemo-audit-progress",
  "skill_md_contents": "---\nname: xmemo-audit-progress\ndescription: Verify project or agent progress claims against an approved baseline, XMemo context, and current artifacts. Use to identify evidence gaps, drift, blockers, and the next action; distinguish claims from verified completion.\n---\n\n# Audit Progress with XMemo\n\nMeasure reality against the approved baseline. Follow\n**baseline → claims → evidence → reconcile → verdict → checkpoint**.\n\n## 1. Recover the governing baseline\n\nUse `recall_context`, `get_project_summary`, `search_memory`, and relevant\n`todo` reads to recover the approved plan, criteria, decisions, last verified\ncheckpoint, and known blockers. Name the governing artifact or memory and flag\nambiguity before auditing.\n\n## 2. Normalize progress claims\n\nBreak the report into atomic claims: changed, tested, deployed, reviewed,\ndocumented, blocked, or deferred. Preserve source agent and artifact/version\nwhen known, but do not treat identity as evidence.\n\n## 3. Verify current evidence\n\nInspect available files, diffs, commits, tests, logs, deployments, or explicit\nuser confirmation. Classify each claim:\n\n- **verified** — direct evidence satisfies the criterion;\n- **partial** — some evidence exists, but the criterion is incomplete;\n- **claimed** — asserted without adequate evidence;\n- **stale** — superseded by newer state;\n- **conflicting** — sources disagree and evidence does not resolve them;\n- **blocked** — a named dependency prevents verification or completion.\n\nAbsence of evidence is not proof of failure. A local test is not deployment\nevidence; a commit is not proof of hosted behavior.\n\n## 4. Return a formal audit\n\nUse:\n\n1. **Audit scope and baseline**\n2. **Verdict** — `on_track`, `at_risk`, `blocked`, or `not_verified`\n3. **Claim matrix** — claim, status, evidence, gap\n4. **Plan drift**\n5. **Risks and blockers**\n6. **Acceptance gaps**\n7. **Exact next action**\n\nWhen requested, create a durable Markdown report using\n`assets/progress-audit-template.md`. Do not write a file for a report-only\nrequest.\n\n## 5. Reconcile XMemo from verified truth\n\nWith authorization, replace the checkpoint via `update_state`, complete or\nupdate TODOs only when their conditions are met, record a milestone with\n`record_event`, correct durable claims with `update_memory`, and preserve new\nlessons with `remember`.\n\nNever save the audit narrative as a transcript or mark completion from an\nagent's confidence alone. Read\n`../xmemo-memory-steward/references/review-playbooks.md`,\n`../xmemo-memory-steward/references/workflows.md`, and\n`../xmemo-memory-steward/references/tool-routing.md` for detailed contracts.\n\n## Shared boundaries\n\nBefore any tool call, read and apply\n[plugin boundaries](../xmemo-memory-steward/references/plugin-boundaries.md).\nUse [tool routing](../xmemo-memory-steward/references/tool-routing.md) for unfamiliar\noperations, [temporal queries](../xmemo-memory-steward/references/temporal-queries.md)\nfor dates or chronology, and [memory policy](../xmemo-memory-steward/references/memory-policy.md)\nbefore writes. Reuse existing authorization; clarify only unresolved scope.\nReport failed or unconfirmed operations without claiming success.\n"
}