second-opinion

second-opinion

⚠️ Tool-managed skill provided by agent-memory (provenance: agent-memory-builtin). Don't edit it in place — it is overwritten on upgrade. To change behavior: fork it under a new skill name, or upstream a genuine fix to the agent-memory project (file an issue in its repo, or bring it to the tool maintainer) for back-port + validation. See SKILLS.md → "Tool-provided (system) skills".

A deliberate fresh-context review ritual. A long session accumulates assumptions and self-trust — the agent that built a solution over-trusts its own trajectory. This skill packages a compact snapshot of the current task so a reviewer with clean memory (a fresh session, or a different vendor) can challenge it. The reviewer's value is precisely that it did not live the session.

Pairs with apply-critique, which consumes the critique the reviewer hands back.

When to use

• Milestone mode — the work looks complete and you're about to close it. This is the highest-value case: the in-session agent is least likely to challenge itself exactly when it feels done.
• Reactive mode — you're blocked, uncertain, the logic seems inconsistent, several designs compete, or the change is high-stakes.

Invoked by the human, on demand. It never runs during ordinary work.

What to do

1. Determine the trigger from how the human invoked you — milestone vs. reactive. Note it in the snapshot's Exchange Intent.

2. Show the security advisory and wait for explicit acknowledgment. Packaging task state for another AI system is a trust-boundary event, even when the reviewer is internal. Print this verbatim and stop until the human types acknowledge (or cancels) — do not generate the snapshot first:

   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
   Fresh-Context Review — Snapshot Advisory
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
   You are about to generate a work-in-progress snapshot for review by another
   AI system (a clean session or a different vendor). Before you share it, ensure:
   
   - no client secrets, credentials, or tokens are included;
   - no personally identifiable information (PII) is exposed;
   - the content is appropriate to share beyond this project's perimeter.
   
   You may prefer a reviewer inside your organization's security boundary. Even
   then, review before sharing — think of it as handing context to a trusted
   collaborator. Power comes with responsibility.
   
   Type "acknowledge" to proceed, or cancel.
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━