name: adr-reviewer description: Review an ExStruct ADR draft for decision quality, overlap with existing ADRs and specs, evidence strength, rollout risk, and human-ownership escalations. Use only after adr-linter reports no unresolved high/medium findings on the current draft, and when you need design-review findings before merge or handoff.
ADR Reviewer
Review the policy decision, not just the document shape.
Read
dev-docs/agents/adr-governance.mddev-docs/agents/adr-criteria.mddev-docs/agents/adr-workflow.mddev-docs/specs/adr-review.md- The target ADR draft
- Related ADRs, relevant public docs under
docs/when public API / CLI / MCP contracts are in scope, internal specs, tests, src paths, and issue / PR context - Existing
adr-linterfindings for the current draft
Workflow
- Confirm the current draft has no unresolved
adr-linterhigh/mediumfindings. Only proceed with design review after that precondition is met. - Read the ADR draft and identify the single policy question it is trying to resolve.
- Check whether the draft overlaps with, contradicts, or should supersede an existing ADR or spec.
- Verify that the cited
Tests,Code, andRelated specsactually support the claims being made, and include relevant publicdocs/pages in scope when the ADR touches public API / CLI / MCP contracts. - Review whether compatibility, rollout, fallback, migration, or safety consequences are covered when relevant.
- Detect human-owned decisions that AI should not settle, including public API break judgment, security or license calls, major directory reorganization, or unresolved product/spec direction.
- Return one verdict:
readyreviseescalate
Output Contract
Return findings first, ordered by severity, and include:
verdictscopedraftrelated ADRspublic docsspecssrctestsissue / PR context
findings
Each finding should include:
typedecision-gapscope-conflictevidence-riskrollout-gapownership-escalation
severitysummarywhy it matterssuggested revisionevidencedraftrelated sources
Also include top-level:
open questionsresidual risks
Do not silently rewrite the ADR text. If the review hits a human-owned decision, return escalate instead of inventing a final policy.