adr-review
Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.
Best use case
adr-review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.
Teams using adr-review should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/adr-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How adr-review Compares
| Feature / Agent | adr-review | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# ADR Review
Multi-agent debate pattern for rigorous ADR validation. Orchestrates 6 specialized agents through structured review rounds until consensus or 10 rounds maximum.
## Quick Start
```text
# Manual triggers:
/adr-review .agents/architecture/ADR-005-api-versioning.md
"review this ADR"
"validate ADR-005"
```
**Automatic Detection**: A Claude Code hook (`Invoke-ADRChangeDetection.ps1`) runs at session start and detects ADR changes, prompting you to invoke this skill. The pre-commit hook also detects staged ADR files and displays a reminder.
| Input | Output | Consensus Required |
|-------|--------|-------------------|
| ADR file path | Debate log + Updated ADR | 6/6 Accept or D&C |
## File Triggers
| Pattern | Location | Events |
|---------|----------|--------|
| `ADR-*.md` | `.agents/architecture/` | create, update, delete |
| `ADR-*.md` | `docs/architecture/` | create, update, delete |
**Detection**: `.claude/skills/adr-review/scripts/Detect-ADRChanges.ps1`
## When to Use
**MANDATORY Triggers** (automatic):
- Architect creates or updates an ADR
- ANY agent modifies `.agents/architecture/ADR-*.md`
**User-Initiated Triggers** (manual):
- User requests ADR review ("review this ADR", "validate this decision")
- User requests multi-perspective validation for strategic decisions
## Agent Roles
| Agent | Focus | Tie-Breaker Role |
|-------|-------|------------------|
| **architect** | Structure, governance, coherence, ADR compliance | Structural questions |
| **critic** | Gaps, risks, alignment, completeness | None |
| **independent-thinker** | Challenge assumptions, surface contrarian views | None |
| **security** | Threat models, security trade-offs | None |
| **analyst** | Root cause, evidence, feasibility | None |
| **high-level-advisor** | Priority, resolve conflicts, break ties | Decision paralysis |
## Debate Protocol
| Phase | Purpose | Details |
|-------|---------|---------|
| **Phase 0** | Related work research | Search issues/PRs for context |
| **Phase 1** | Independent review | Each agent reviews ADR |
| **Phase 2** | Consolidation | Identify consensus and conflicts |
| **Phase 3** | Resolution | Propose updates for P0/P1 issues |
| **Phase 4** | Convergence check | Agents vote: Accept/D&C/Block |
**Consensus**: All 6 agents Accept OR Disagree-and-Commit. Max 10 rounds.
See [references/debate-protocol.md](references/debate-protocol.md) for full phase details.
## Deletion Workflow
| Phase | Purpose |
|-------|---------|
| **D1** | Detection - identify deleted ADR |
| **D2** | Impact assessment - find dependencies |
| **D3** | Archival decision - archive accepted ADRs |
| **D4** | Cleanup - update references |
See [references/deletion-workflow.md](references/deletion-workflow.md) for full workflow.
## Issue Resolution
| Priority | Requirement | Gate |
|----------|-------------|------|
| **P0** | Must resolve | BLOCKING |
| **P1** | Resolve OR defer with issue | BLOCKING |
| **P2** | Document | Non-blocking |
See [references/issue-resolution.md](references/issue-resolution.md) for deferral protocol.
## Phase 4: Strategic Review (Principal-Level Validation)
After structural and technical review, apply strategic lenses:
### Strategic Validation Checklist
#### Chesterton's Fence (Change Justification)
- [ ] If removing/changing existing patterns: Original purpose documented
- [ ] Investigation evidence provided (git archaeology, interviews, documentation)
- [ ] Confirmation original problem no longer exists
- [ ] Assessment: [PASS | FAIL | N/A]
#### Path Dependence (Irreversibility Recognition)
- [ ] Historical constraints identified and documented
- [ ] Reversibility assessment complete (rollback capability, vendor lock-in)
- [ ] Migration/exit strategy defined if adding dependencies
- [ ] Irreversible decisions explicitly flagged and justified
- [ ] Assessment: [PASS | FAIL | N/A]
#### Core vs Context (Investment Prioritization)
- [ ] Capability classified as Core (differentiating) or Context (commodity)
- [ ] If building Context: Justification for not buying/outsourcing
- [ ] If Core: Competitive differentiation explained
- [ ] Assessment: [PASS | FAIL | N/A]
#### Second-System Effect (Over-Engineering Detection)
- [ ] If replacing existing system: Scope boundaries explicit
- [ ] Feature list justified (not "everything we didn't do last time")
- [ ] Simplicity preservation strategy documented
- [ ] Assessment: [PASS | FAIL | N/A]
### Strategic Review Verdict
**Overall Strategic Assessment**: [APPROVED | CONCERNS | REJECTED]
**Blocking Issues**:
- [Strategic issue 1 with required mitigation]
- [Strategic issue 2 with required mitigation]
**Recommendations**:
- [Strategic improvement 1]
- [Strategic improvement 2]
## Scripts
| Script | Purpose |
|--------|---------|
| `Detect-ADRChanges.ps1` | Detect ADR file changes for auto-trigger |
```powershell
# Basic detection
& .claude/skills/adr-review/scripts/Detect-ADRChanges.ps1
# Compare to specific commit
& .claude/skills/adr-review/scripts/Detect-ADRChanges.ps1 -SinceCommit "abc123"
```
## Verification Checklist
After skill invocation:
- [ ] Debate log exists at `.agents/critique/ADR-NNN-debate-log.md`
- [ ] ADR status updated (proposed/accepted/needs-revision)
- [ ] All P0 issues addressed or documented
- [ ] Dissent captured for Disagree-and-Commit positions
- [ ] Recommendations provided to orchestrator
## Anti-Patterns
| Avoid | Why | Instead |
|-------|-----|---------|
| Single-agent ADR review | Misses domain expertise | Use full 6-agent debate |
| Skipping Phase 0 | Duplicates existing work | Always research first |
| Ignoring D&C dissent | Loses important context | Document all reservations |
| Manual ADR monitoring | Error-prone | Use Detect-ADRChanges.ps1 |
| Deleting accepted ADRs without archive | Loses knowledge | Always archive accepted ADRs |
## References
| Document | Content |
|----------|---------|
| [debate-protocol.md](references/debate-protocol.md) | Full Phases 0-4 workflow |
| [deletion-workflow.md](references/deletion-workflow.md) | Phases D1-D4 workflow |
| [issue-resolution.md](references/issue-resolution.md) | P0/P1/P2 handling and deferral |
| [artifacts.md](references/artifacts.md) | Output formats and templates |
| [agent-prompts.md](references/agent-prompts.md) | Detailed agent prompt templates |Related Skills
address-review
Use when addressing PR review comments from Copilot, Claude, or human reviewers. Critically assesses each comment, recommends action (implement/push-back/discuss), and executes appropriately.
add-review-comment
Add a review comment to a GitHub pull request.
ad-review
Quality review ads before launch by verifying hook strength, checking proof elements, evaluating CTA effectiveness, and assessing visual quality and authenticity. Use as final check before launching creative or when reviewing team submissions.
actionable-review-format-standards
Standardized output format for code reviews with severity labels, file:line references, and fix code snippets. Use when generating review reports that need consistent, actionable feedback structure.
act-code-reviewer
Review JusticeHub code against ACT ecosystem values. Enforces cultural protocols, ALMA principles, and regenerative design.
accessibility-review
Reviews UI for accessibility issues against WCAG 2.1/2.2 AA. Triggers on "is this accessible?", "check accessibility", or contrast/a11y review requests.
academic-reviewer
Expert guidance for reviewing academic manuscripts submitted to journals, particularly in political science, economics, and quantitative social sciences. Use when asked to review, critique, or provide feedback on academic papers, research designs, or empirical strategies. Emphasizes methodological rigor, causal identification strategies, and constructive feedback on research design.
ac-qa-reviewer
Quality assurance review for implementations. Use when reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality.
a11y-review
Controleer toegankelijkheid conform WCAG 2.1 AA. Gebruik bij het reviewen van templates, CSS of HTML, of wanneer de gebruiker vraagt om toegankelijkheid te checken.
agent-ops-docker-review
Docker image reviews, optimization, and step-building guidance. Analyzes Dockerfiles for best practices, security issues, and anti-patterns.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.