architecture-reviewer
Skill4 starsChanged 2 months agoApache-2.0View on GitHub
Review architectural changes for coupling, blast radius, and long-term impact. Use when evaluating system design changes, cross-service dependencies, API changes, or infrastructure modifications. Triggers on "architecture review", "impact analysis", "blast radius", "coupling review", "dependency analysis", "breaking change", "migration review", "system design review".
9 other projects use a version of this.
Adopted by
Most recently taken up by
- JuanMarchetto/agent-skillstheir own version, first seen Nov 8, 2026
- cobusgreyling/grok-build-arsenaltheir own version, first seen Nov 8, 2026
- Mathews-Tom/armorytheir own version, first seen Nov 1, 2026
- monsefchafik/claude-code-skillstheir own version, first seen Oct 20, 2026
- mrenigmatic19/claude_skillstheir own version, first seen Oct 8, 2026
- domehahn/skiltheir own version, first seen Jul 28, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- Mathews-Tom/armory★ 340same name
- shep-ai/shep★ 277same name
- wolulabs/hermes-founder-os★ 18same name
- cobusgreyling/grok-build-arsenal★ 6same name
- JuanMarchetto/agent-skills★ 5same name
- domehahn/skil★ 1same name
- nileshteji/skills★ 1same name
- monsefchafik/claude-code-skills★ 0same name
- mrenigmatic19/claude_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- agent-notepadSkill
- backend-service-auditorSkill
- channel-listenerSkill
- code-reviewerSkill
- coder-file-transferSkill
- cold-start-generatorSkill
- creating-skillsSkill
- critical-thinkingSkill
- dark-factory-buildSkill
- dependency-risk-auditorSkill
- df-adversary-gateSkill
- df-app-walkthroughSkill
- df-context-storeSkill
- df-data-transform-lensSkill
- df-dispatch-subagentsSkill
- df-infrastructureSkill
- df-observabilitySkill
- df-product-ownerSkill
- df-qaSkill
- df-solution-architectSkill
- df-tdd-developerSkill
- df-ui-verifySkill
- df-video-intakeSkill
- dx-maintainability-reviewerSkill
- frontend-auditorSkill
- handoffSkill
- microservices-architectSkill
- production-readiness-reviewerSkill
- repo-docsSkill
- requirements-discoverySkill
- sc-auditSkill
- sc-devSkill
- scope-initSkill
- scope-retireSkill
- security-threat-modelerSkill
- service-mapperSkill
- test-quality-gatekeeperSkill
- vercel-react-best-practicesSkill
- vinculum-loopSkill
- vinculum-mapSkill
- web-design-guidelinesSkill
- work-autonomouslySkill
The file
Files
Architecture & Change Impact Reviewer
System-level reviewer for architectural changes. Assesses whether changes fit the current architecture, introduce hidden coupling, or create long-term operational risk.
When to Use
- Reviewing changes that touch multiple services/layers
- Evaluating new cross-service dependencies
- Assessing API or schema changes for compatibility
- Reviewing infrastructure or deployment changes
- Analyzing migration strategies
- Evaluating the "future cost" of architectural decisions
Review Workflow
On EVERY invocation, execute these steps in order:
Step 1: Identify Affected Layers
Map which architectural layers are touched:
┌─────────────────────────────────────────────────────┐
│ FRONTEND │
│ (React/Next/Vue, mobile apps, CLI tools) │
├─────────────────────────────────────────────────────┤
│ API GATEWAY │
│ (routing, auth, rate limiting) │
├─────────────────────────────────────────────────────┤
│ BACKEND SERVICES │
│ (APIs, workers, microservices) │
├─────────────────────────────────────────────────────┤
│ SMART CONTRACTS / CHAIN │
│ (on-chain logic, oracles, bridges) │
├─────────────────────────────────────────────────────┤
│ DATA LAYER │
│ (databases, caches, queues, event stores) │
├─────────────────────────────────────────────────────┤
│ INFRASTRUCTURE │
│ (K8s, cloud resources, networking, secrets) │
└─────────────────────────────────────────────────────┘Mark each layer: ✅ Affected | ○ Unchanged | ⚠️ Indirectly Impacted
Step 2: Scan Recent Changes
# Current changes
git diff --stat
git diff --name-only
# Recent commits for context
git log --oneline -20
# Find cross-cutting changes
git diff --name-only | xargs -I {} dirname {} | sort -uIdentify:
- What modules/services are directly changed?
- What interfaces (APIs, events, schemas) are modified?
- Are there database migrations?
Step 3: Build Dependency Graph
Map the impacted components and their dependencies:
[Changed Component]
│
├──► [Direct Dependency 1] ──► [Transitive Dep]
│
├──► [Direct Dependency 2]
│
└──► [Shared Resource] ◄── [Other Consumer]Identify:
- Upstream dependencies (what this component calls)
- Downstream consumers (what calls this component)
- Shared resources (DBs, caches, queues, configs)
- Implicit dependencies (timing, ordering, shared state)
Step 4: Evaluate Blast Radius
Assess failure scenarios:
| Failure Mode | Blast Radius | Mitigation |
| Component crashes | [scope] | [strategy] |
| Slow response | [scope] | [strategy] |
| Bad data produced | [scope] | [strategy] |
| Deployment fails | [scope] | [strategy] |
See CHECKLIST.md for the complete review checklist.
Output Format
A) What Changed
Layers affected: [Frontend, Backend, Data]
Services modified: [service-a, service-b]
Interfaces changed: [API endpoints, event schemas, DB tables]
Lines of code: [+added / -removed]B) Dependency Analysis
Direct dependencies: [list]
Downstream consumers: [list]
Shared resources: [list]
Cross-service calls: [new/modified/removed]C) Risk Assessment
Use severity levels:
| Severity | Icon | Meaning |
| CRITICAL | :red_circle: | Breaking change, data loss risk, security hole |
| HIGH | :orange_circle: | Significant coupling, complex rollback |
| MEDIUM | :yellow_circle: | Operational complexity, performance risk |
| LOW | :white_circle: | Minor concern, tech debt |
| INFO | :blue_circle: | Observation, suggestion |
For each risk:
### [SEVERITY] Risk Title
**Category:** Coupling / Data / Contracts / Operations / Migration
**Description:** [What is the risk]
**Blast Radius:** [What fails if this goes wrong]
**Mitigation:** [How to reduce risk]D) Operational Impact
Deploy order: [sequence if any]
Rollback complexity: [simple/complex/impossible]
Feature flags needed: [yes/no, which]
Dual-write period: [if applicable]
Data migration: [if applicable]
Monitoring additions: [what to watch]E) Recommendations
1. [Highest priority recommendation]
2. [Second priority]
3. ...
Future considerations:
- [What this makes harder/easier for future changes]F) Approval Decision
[ ] APPROVE - No significant architectural concerns
[ ] APPROVE WITH CONDITIONS - Address [specific items] before merge
[ ] REQUEST CHANGES - [Blocking concerns that must be resolved]
[ ] NEEDS DISCUSSION - Escalate to architecture review meetingQuick Commands
# Find all service dependencies
grep -rn "import.*from\|require(" --include="*.ts" | grep -v node_modules
# Find API calls between services
grep -rn "fetch\|axios\|http\." --include="*.ts" --include="*.go"
# Find database migrations
ls -la migrations/ db/migrations/ prisma/migrations/ 2>/dev/null
# Find event publishers/consumers
grep -rn "publish\|emit\|subscribe\|consume" --include="*.ts"
# Check for new dependencies
git diff package.json go.mod requirements.txt Cargo.toml 2>/dev/nullResources
- CHECKLIST.md - Complete review checklist
- PATTERNS.md - Common architectural anti-patterns
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

