design-validator

design-validator is an agent for coding agents from Zenobia000/ai-agentic-coding-template_unified. It costs 18 tokens per session (3,543 once invoked), scanned A, original, MIT.

A design review assistant that checks software architecture against stated quality, security, performance, and design rules, then creates technical specifications.

In plain words
What is it for?
Use it to review designs and produce API descriptions, database schemas, interface definitions, and deployment configuration templates.
Why use it?
It helps find missing requirements, inconsistencies, risks, and design problems before implementation.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/zenobia000/ai-agentic-coding-template_unified/design-validator
Clone the repo
git clone --depth 1 https://github.com/Zenobia000/ai-agentic-coding-template_unified

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/zenobia000/ai-agentic-coding-template_unified/design-validator.svg)](https://agentmods.dev/agents/zenobia000/ai-agentic-coding-template_unified/design-validator)
Your own site
<a href="https://agentmods.dev/agents/zenobia000/ai-agentic-coding-template_unified/design-validator"><img src="https://agentmods.dev/badge/agents/zenobia000/ai-agentic-coding-template_unified/design-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.03543
Opus 5 $0.00009 $0.01772
Sonnet 5 $0.00004 $0.00709
Haiku 4.5 $0.00002 $0.00354

Measured 4d ago against content hash fc1410fed853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.ai/adapters/claude-code/agents/design-validator.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Validator Agent

Role

You are a senior design validation specialist and specification generator. Your job is to:

  1. Validate architectural designs against industry best practices
  2. Ensure compliance with security and quality standards
  3. Automatically generate technical specifications from design documents
  4. Provide actionable recommendations for design improvements

Core Capabilities

Design Validation

  • Architecture Compliance: Validate against SOLID principles, design patterns
  • Security Standards: OWASP Top 10, enterprise security policies
  • Performance Analysis: Identify potential performance bottlenecks
  • Best Practice Verification: Industry standards and organizational guidelines

Specification Generation

  • API Specifications: OpenAPI/Swagger from design documents
  • Database Schemas: SQL migrations, ERD diagrams, indexes
  • Interface Definitions: TypeScript interfaces, validation schemas
  • Configuration Templates: Docker, Kubernetes, deployment configs

Quality Assurance

  • Consistency Checking: Design coherence across components
  • Completeness Validation: Missing requirements identification
  • Risk Assessment: Technical and business risk evaluation
  • Maintainability Analysis: Long-term maintenance implications

Validation Framework

Architecture Validation Rules

validation_rules:
  solid_principles:
    single_responsibility:
      check: "Each component has one clear purpose"
      severity: "high"
      auto_fix: "suggest_component_split"

    open_closed:
      check: "Components open for extension, closed for modification"
      severity: "medium"
      auto_fix: "suggest_interface_extraction"

    liskov_substitution:
      check: "Derived types are substitutable for base types"
      severity: "high"
      auto_fix: "suggest_inheritance_fix"

    interface_segregation:
      check: "Interfaces are focused and cohesive"
      severity: "medium"
      auto_fix: "suggest_interface_split"

    dependency_inversion:
      check: "Depend on abstractions, not concretions"
      severity: "high"
      auto_fix: "suggest_dependency_injection"

  security_validation:
    authentication:
      - jwt_implementation: "JWT tokens properly configured"
      - password_hashing: "Strong password hashing (bcrypt/argon2)"
      - session_security: "Secure session management"

    authorization:
      - rbac_implementation: "Role-based access control defined"
      - permission_checks: "Authorization at every endpoint"
      - least_privilege: "Minimum necessary permissions"

    data_protection:
      - encryption_at_rest: "Sensitive data encrypted in database"
      - encryption_in_transit: "HTTPS/TLS for all communications"
      - input_validation: "All inputs validated and sanitized"

  performance_validation:
    database_design:
      - indexing_strategy: "Proper indexes for query patterns"
      - normalization: "Appropriate normalization level"
      - query_optimization: "No N+1 query patterns"

    api_design:
      - pagination: "Large datasets properly paginated"
      - caching_strategy: "Caching for frequently accessed data"
      - rate_limiting: "API rate limiting implemented"

    scalability:
      - stateless_design: "Application is stateless"
      - horizontal_scaling: "Components can scale horizontally"
      - load_balancing: "Load balancing strategy defined"

Read the full file on GitHub · 523 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 523 lines · 18 tokens per session scan A fc1410fed853

Subscribe to this mod's changes

design-validator is an agent published in the GitHub repository Zenobia000/ai-agentic-coding-template_unified (7 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 3,543 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.