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 vignesh2027/AI-AGENT-SKILLS --skill architecture-designgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote 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/vignesh2027/ai-agent-skills/architecture-design)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/architecture-design"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/architecture-design/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/vignesh2027/ai-agent-skills/architecture-design"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/architecture-design.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 | $0.00014 | $0.00747 |
| Opus 5.5 | $0.00006 | $0.00299 |
| Sonnet 5.5 | $0.00003 | $0.00149 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
architecture-design 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Architecture design is the discipline of making the decisions that are hard to reverse later. Good architecture is not the most elegant — it is the simplest design that satisfies constraints today and can be evolved tomorrow. Every architecture decision has costs; this skill makes them explicit.
When to Use
- Before building any system with more than 2 components
- When adding a new service to an existing system
- When the existing architecture is causing repeated failures
- Before selecting a technology stack
Process
Step 1: Establish the constraints
List: scale targets, latency requirements, consistency requirements, team size, deployment environment, budget, regulatory constraints. Architecture that ignores constraints is fiction.
Step 2: Identify the quality attributes
Rank the system's quality attributes in priority order: availability, consistency, latency, throughput, security, maintainability, cost. You cannot optimize all of them — make the trade-offs explicit.
Step 3: Define the component boundaries
Identify the major components and their responsibilities. Apply the Single Responsibility Principle at the system level: each component should own one thing well.
Step 4: Define the data flow
Draw how data moves through the system. Where does it originate? Where is it stored? Where is it transformed? Where does it exit? This reveals coupling and bottlenecks.
Step 5: Choose synchronous vs async communication
For each inter-component call: does the caller need the result immediately? If no, use async. Sync calls are coupling in disguise.
Step 6: Design for failure
For each component and connection: what happens when it fails? Design for partial failure, not just total failure. Document: retry strategy, circuit breaker, fallback, timeout.
Step 7: Plan the data model at boundaries
Define what data crosses each boundary. Avoid sharing databases between services. Define API contracts between components.
Step 8: Write an ADR (Architecture Decision Record)
Document: the decision, the context, the alternatives considered, the rationale, and the consequences. An architecture without ADRs cannot be maintained.
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.
- 2mo ago First seen · 76 lines · 14 tokens per session scan A 4ae8f264c738
architecture-design is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 747 once invoked, about $0.0001 per session on Opus 5.5. 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.
architecture-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architecture-designvignesh2027/AI-AGENT-SKILLS | Skill | 2 | 2mo ago | MIT | A | 14 | Claude Code, Codex |
| cw-gatesHmbown/Codewhale | Skill | 41k | 1mo ago | MIT | A | 48 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| eval-dataset-designbojieli/ai-agent-book | Skill | 57k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| memory-systembojieli/ai-agent-book | Skill | 57k | 1mo ago | Apache-2.0 | A | 95 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |
| loongsuite-pilot-insightalibaba/loongsuite-pilot | Skill | 242 | yesterday | Apache-2.0 | A | 111 | Claude Code, Codex |