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 ddddjaak/se-skills --skill architecture-designgit clone --depth 1 https://github.com/ddddjaak/se-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/ddddjaak/se-skills/architecture-design)<a href="https://agentmods.dev/skills/ddddjaak/se-skills/architecture-design"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-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/ddddjaak/se-skills/architecture-design"><img src="https://agentmods.dev/badge/skills/ddddjaak/se-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 | $0.00121 | $0.04355 |
| Opus 5 | $0.00060 | $0.02178 |
| Sonnet 5 | $0.00024 | $0.00871 |
| Haiku 4.5 | $0.00012 | $0.00436 |
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 10d 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Design
Overview
System requirements say what the system must do. Architecture design says how the system will be built to do it. This skill bridges the gap between requirements and implementation — decomposing the system into modules, defining every interface, analyzing cross-cutting constraints, and documenting the trade-offs behind every non-trivial decision.
A good architecture document is the answer key for every downstream question: "which module owns this feature?", "what does module A promise to module B?", "why did we choose this protocol over that one?". Without it, every implementer answers these differently, and integration becomes a discovery process instead of an execution plan.
Architecture design is to SE what task-breakdown planning is to software development — but for hardware-software system architecture rather than implementation tasks.
When to Use
- Structured system requirements exist (output of
requirements-decompose) and are confirmed - Starting a new chip application design from scratch
- Adding a major subsystem (new power domain, new communication interface, new safety feature) to an existing design
- Evaluating architecture alternatives against a set of quantified requirements
- A downstream skill (
spec-authoring) detects an architecture decision that was assumed but never documented - A design review surfaces interface or module-boundary issues that require architectural resolution
When NOT to use:
- Requirements are not yet decomposed and confirmed (run
requirements-decomposefirst) - The change is limited to a single module's internal implementation with no interface impact
- Pure implementation task ("write the driver for this already-specified interface")
- The architecture document already exists and only needs a small clarification (edit the document directly)
The Process
DECOMPOSE ──→ INTERFACE ──→ CONSTRAINT ──→ TRADE-OFF ──→ DOCUMENT
│ │ │ │ │
▼ ▼ ▼ ▼ ▼
Module Define Analyze Evaluate Produce
breakdown every IF cross-cutting alternatives architecture
precisely constraints & decide document
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.
- 10d ago First seen · 300 lines · 121 tokens per session scan A beb03ffde950
architecture-design is a skill published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 4,355 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…