Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

adr-review — Claude Code skill: what it does, how to install

Reviews git diffs against accepted Architecture Decision Records to detect violations, forbidden patterns, and architecture drift before merging code.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add ruvnet/ruflo --skill adr-review -a claude-code
Open on GitHub

What adr-review does

The skill inspects changes between main and the current branch using git diff. For every modified file, it searches for ADR identifiers, scans the docs/adr/ directory with Grep, and runs semantic searches via the ruflo-core MCP tools.

Analysis focuses exclusively on accepted records. It reads the Decision and Consequences sections to spot code that contradicts established architecture, implements rejected technologies, or alters modules against explicit warnings.

To trace dependencies, the skill queries the adr-edges namespace for supersedes, amends, and depends-on links. Running adr-index beforehand is necessary if that memory namespace is empty, because outdated decisions would otherwise go unnoticed. The output is a structured report with violations, warnings, and unlinked changes.

What it helps with

  • detect code violations against accepted architecture records
  • catch usage of rejected technologies or design patterns
  • verify modified files against documented architectural constraints
  • identify references to superseded or outdated ADR documents

Example prompts for the agent

  • Review changes in the current branch against accepted ADRs.
  • Run adr-review for branch staging and list all architectural violations.
  • Compare the latest diff with docs/adr/ and generate a compliance report.

How to install adr-review

1Skills CLI (Vercel)

npx skills add ruvnet/ruflo --skill adr-review -a claude-code

2Manually: put the files in place

~/.claude/skills/adr-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/adr-review/

From the same set104

The whole set →
ruflo ruvnet This skill adds multi-agent orchestration, memory, routing, and MCP tools to a project. Use it for swarm tasks and multi-step workflows. Claude Code CX Codex Cursor +1 4,000installs Swarm Orchestration ruvnet Skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. Claude Code CX Codex Cursor +1 2,100installs github-project-management ruvnet Turns issue triage and board upkeep into gh and ruv-swarm calls: labels, subtasks, duplicate lookup. Useful when the tracker holds more tickets than order. Claude Code CX Codex Cursor +1 1,400installs github-workflow-automation ruvnet Automates GitHub Actions with AI agent coordination. Generates optimised pipelines, manages pull requests, analyzes failed runs, and deploys updates with risk assessment. Claude Code CX Codex Cursor +1 1,300installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs stream-chain ruvnet Chains sequential agent steps together using streaming JSON flow and provides ready-to-run pipelines. Claude Code CX Codex Cursor +1 1,200installs flow-nexus-swarm ruvnet Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs performance-analysis ruvnet Detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. Claude Code CX Codex Cursor +1 1,200installs

Similar

mantis-plan official google Generates a targeted security review plan based on your threat model and historical findings. Run at the start of a review campaign to map code boundaries and prioritize what to check. Claude Code CX Codex Cursor +1 1,600installs mantis-summarize official google Builds a security-focused codebase map with mantis-summary.md files in each directory. Reduces token overhead during planning and research. Claude Code CX Codex Cursor +1 1,600installs trailmark trailofbits Builds and inspects multi-language code graphs to trace taint propagation, map attack surfaces, and prioritize security audits. Claude Code CX Codex Cursor +1 4,000installs verify Yeachan-Heo Turns "it should work" into evidence you can read: which check ran, what passed, and what stayed unverified. Claude Code CX Codex Cursor +1 642installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs codebase-design Matt Pocock This skill helps design modules with small interfaces and hidden complexity. Use it when refactoring code, choosing a seam, or making tests easier to write. Claude Code 850,344installs

Questions about adr-review

How to install adr-review in Claude Code?

Run npx skills add ruvnet/ruflo --skill adr-review -a claude-code in your terminal.

What does adr-review verify?

It checks your git diff against accepted ADRs in docs/adr/. The skill flags contradictions to agreed decisions, rejected patterns, and broken module constraints.

What is required before checking ADR relationships?

If the adr-edges memory namespace is unpopulated, run adr-index first. The skill needs this graph to detect dependencies and superseded architectural decisions.

Source text

SKILL.md · MIT 
---
name: adr-review
description: Review code changes against accepted ADRs for compliance violations
argument-hint: "[--branch BRANCH]"
allowed-tools: mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-recall mcp__plugin_ruflo-core_ruflo__memory_list mcp__plugin_ruflo-core_ruflo__memory_search Bash Read Grep Glob
---

# ADR Review

Review code changes against accepted Architecture Decision Records to detect violations, drift, and non-compliance.

## When to use

Before merging a PR, after significant code changes, or as part of a periodic compliance check. Use this to ensure code changes respect the architectural decisions the team has agreed upon.

## Steps

1. **Get diff** -- Run `git diff main...HEAD --name-only` (or the specified branch) to list changed files. Then run `git diff main...HEAD` to get the full diff content.

2. **Find relevant ADRs** -- For each changed file:
   - `Grep` the file for ADR references (`ADR-\d+`)
   - `Grep` `docs/adr/` for ADRs that mention the changed file paths or modules
   - Call `mcp__plugin_ruflo-core_ruflo__memory_search` with the file path and change summary to find semantically related ADRs

3. **Load ADR content** -- `Read` each relevant ADR file. Focus on:
   - The **Decision** section (what was decided)
   - The **Status** (only enforce "accepted" ADRs)
   - The **Consequences** (expected constraints)

4. **Check for violations** -- Analyze each changed file against its relevant ADRs:
   - Does the code change contradict an accepted decision?
   - Does it use a technology/pattern that an ADR explicitly rejected?
   - Does it modify a module in a way the ADR's consequences warned against?
   - Is the code referencing a deprecated or superseded ADR?

5. **Query relationship graph** -- Call `mcp__plugin_ruflo-core_ruflo__memory_list` with namespace `adr-edges` (rows are keyed `<relation>:<from>__<to>` with relation `supersedes`, `amends` or `depends-on`) to check if any referenced ADR has been superseded. If the namespace is empty, run `adr-index` first. If a referenced ADR is superseded, flag that the code references an outdated decision.

6. **Report** -- Present findings as a compliance report:
   ```
   ## ADR Compliance Report

   ### Violations
   - [ ] <file>:<line> — violates ADR-NNN: <reason>

   ### Warnings
   - [!] <file> references superseded ADR-NNN (replaced by ADR-MMM)

   ### Compliant
   - [x] <file> — consistent with ADR-NNN

   ### Unlinked Changes
   - [?] <file> — no ADR coverage (consider creating one)
   ```

7. **Suggest actions** -- For each violation, suggest whether to update the code or propose a new ADR to supersede the violated one.

© ruvnet · MIT · ruvnet/ruflo

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor