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.
npx skills add DauQuangThanh/hanoi-rainbow --skill architecture-design-reviewgit clone --depth 1 https://github.com/DauQuangThanh/hanoi-rainbowWrote 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.
[](https://agentmods.dev/skills/dauquangthanh/hanoi-rainbow/architecture-design-review)<a href="https://agentmods.dev/skills/dauquangthanh/hanoi-rainbow/architecture-design-review"><img src="https://agentmods.dev/badge/skills/dauquangthanh/hanoi-rainbow/architecture-design-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dauquangthanh/hanoi-rainbow/architecture-design-review"><img src="https://agentmods.dev/badge/skills/dauquangthanh/hanoi-rainbow/architecture-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.02321 |
| Opus 5 | $0.00041 | $0.01161 |
| Sonnet 5 | $0.00016 | $0.00464 |
| Haiku 4.5 | $0.00008 | $0.00232 |
Grade A, and why
architecture-design-review 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Design Review
Conduct systematic architecture design reviews to validate system design, assess quality attributes, evaluate technology choices, and identify risks before implementation.
Review Process
Follow this structured approach for comprehensive architecture reviews:
1. Gather Architecture Documentation
Collect required materials:
Required Documents:
- Architecture diagrams (C4: Context, Container, Component)
- Architecture Decision Records (ADRs) with rationale and alternatives
- Technical specifications and non-functional requirements (performance, scalability, security)
- Data models, schemas, and API specifications
- Technology stack with justifications
- Deployment and infrastructure diagrams
Context Information:
- Business constraints (budget, timeline, compliance requirements)
- Performance targets (quantified: response time, throughput)
- Scalability goals (user growth, data volume projections)
- Security requirements (authentication model, data protection, compliance)
- Integration requirements (internal/external systems, APIs)
2. Assess Architecture Style and Patterns
Validate architecture style appropriateness:
Style-Requirement Fit:
- Monolithic: Small teams (<10), simple domains, <1000 users
- Microservices: Large teams (>20), complex domains, >100K users
- Serverless: Event-driven, variable load, stateless operations
- Event-Driven: Asynchronous workflows, loose coupling, high throughput
Pattern Assessment:
☐ Architecture style matches requirements (scale, team, complexity)
☐ Service boundaries align with business domains (DDD)
☐ Communication patterns appropriate (sync vs async)
☐ Data management strategy clear (per-service vs shared DB)
☐ Integration patterns documented (gateway, mesh, events)
☐ Deployment model specified (containers, VMs, serverless)
Anti-Pattern Detection:
- Big Ball of Mud: No structure, tight coupling, shared database
- God Service: Single service handling multiple domains
- Chatty Communication: Excessive inter-service calls (>5/request)
- Distributed Monolith: Services coupled through shared database
- Golden Hammer: Same technology for all problems
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/anti-patterns.md 14 KB
- references/api-design.md 230 B
- references/application-security.md 247 B
- references/architecture-review-process.md 1.7 KB
- references/authentication-and-authorization.md 271 B
- references/best-practices-for-architecture-reviews.md 832 B
- references/caching-strategy.md 173 B
- references/common-patterns-to-validate.md 1.3 KB
- references/cost-analysis.md 341 B
- references/data-consistency.md 208 B
- references/data-management.md 280 B
- references/data-scalability.md 158 B
- references/data-storage-strategy.md 165 B
- references/database-selection.md 216 B
- references/disaster-recovery.md 243 B
- references/external-integrations.md 329 B
- references/fault-tolerance.md 238 B
- references/high-availability-design.md 229 B
- references/horizontal-scalability.md 221 B
- references/infrastructure-costs.md 212 B
- references/infrastructure.md 207 B
- references/monitoring-and-observability.md 299 B
- references/operational-readiness.md 291 B
- references/quality-attributes.md 16 KB
- references/review-checklists.md 21 KB
- references/review-report-template.md 74 B
- references/review-severity-levels.md 651 B
- references/risk-assessment.md 396 B
- references/service-boundaries-microservices.md 276 B
- references/testing-strategy.md 203 B
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.
- 12d ago First seen · 251 lines · 81 tokens per session scan A d6c2d4403d3c
architecture-design-review is a skill published in the GitHub repository DauQuangThanh/hanoi-rainbow (17 stars, last pushed 7mo ago), licensed MIT. It adds 81 tokens to every session and 2,321 once invoked, about $0.0004 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.
Other skills, from other repositories
code-review-hardening
Use this skill for rigorous, structured code review with a self-repair loop. Applies change-type-aware strategies (feat, fix, hotfix, refactor, migrate, docs). Findings are severity-classified, then auto-fixed where possible. Triggers on PR reviews, code review requests, or when reviewing any change set.
quality-grading
Use this skill to grade code, specifications, or design documents across four quality dimensions using a 1-5 scoring scale. In grade-and-fix mode, the skill auto-improves artifacts scoring below 5 without prompting. Invoke when you want consistent quality assessment on design, implementation, or specification with…
agent-work-auditor
Unified auditing skill for AI agent workflows. Provides change-type-aware, artifact-adaptive auditing with self-fix capabilities. Works standalone or with spec-driven extensions. Three-layer architecture: core (always active), modules (per-type), extensions (auto-detected).
spec-driven-development
Spec-first workflow where an executable, testable specification is written before code and becomes the single source of truth that tests verify against, flowing spec → acceptance criteria → tasks → implementation.
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
bmad-review-adversarial-general
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something.