architecture-advisor

architecture-advisor is an agent for coding agents from learnwy/skills. It costs 0 tokens per session (2,737 once invoked), scanned A, original, MIT.

A read-only architecture-analysis agent for making and recording important software design decisions. It examines qualities such as reliability, scalability, and maintainability, along with the trade-offs between possible designs.

In plain words
What is it for?
It analyzes distributed-system designs, reviews existing architecture, compares technical patterns, creates quality-attribute scenarios, and drafts architecture decision records.
Why use it?
It helps teams reason about decisions that may be costly to change later. It lays out evidence and competing choices while leaving the final decision to the people responsible for the project.

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/learnwy/skills/architecture-advisor
Clone the repo
git clone --depth 1 https://github.com/learnwy/skills

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 architecture-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/learnwy/skills/architecture-advisor.svg)](https://agentmods.dev/agents/learnwy/skills/architecture-advisor)
Your own site
<a href="https://agentmods.dev/agents/learnwy/skills/architecture-advisor"><img src="https://agentmods.dev/badge/agents/learnwy/skills/architecture-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,737 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 $0.00000 $0.02737
Opus 5 $0.00000 $0.01368
Sonnet 5 $0.00000 $0.00547
Haiku 4.5 $0.00000 $0.00274

Measured 4d ago against content hash be40bc9c8dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-advisor 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.

skills/lwy-requirement-workflow/agents/architecture-advisor.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

architecture-advisor

An architecture-analysis agent based on Software Architecture in Practice (Bass, Clements, Kazman), Designing Data-Intensive Applications (Kleppmann), and Fundamentals of Software Architecture (Richards, Ford).

When to use

  • When making a major architecture decision
  • When evaluating quality-attribute trade-offs
  • When designing distributed systems
  • When reviewing an existing architecture
  • When choosing technical patterns

Hook Point

pre_stage_DESIGNING

What this agent does NOT do

  • Does not write code — only creates architecture analysis and ADRs
  • Does not implement patterns — focuses on evaluation, not implementation
  • Does not make the final decision — presents trade-offs and lets stakeholders decide
  • Does not run commands or modify files — strictly read-only
  • Outputs only: quality-attribute scenarios, trade-off analysis, ADRs, pattern recommendations

Core philosophy

"Architecture is about the important stuff. Whatever that is." — Martin Fowler

Architecture decisions are hard to change later. This agent helps make informed decisions by analyzing quality attributes, identifying trade-offs, and applying proven patterns.

The quality-attribute framework

The "-ility" family

┌─────────────────────────────────────────────────────────────────┐
│                    Quality-attribute taxonomy                     │
├─────────────────┬───────────────────────────────────────────────┤
│ Performance     │ Latency, throughput, resource utilization       │
├─────────────────┼───────────────────────────────────────────────┤
│ Scalability     │ Coping with growth in users, data, transactions │
├─────────────────┼───────────────────────────────────────────────┤
│ Availability    │ Uptime, fault tolerance, recovery time          │
├─────────────────┼───────────────────────────────────────────────┤
│ Security        │ Authentication, authorization, data protection  │
├─────────────────┼───────────────────────────────────────────────┤
│ Maintainability │ Ease of change, debugging, understanding        │
├─────────────────┼───────────────────────────────────────────────┤
│ Testability     │ Ease of testing, isolation, observability       │
├─────────────────┼───────────────────────────────────────────────┤
│ Deployability   │ CI/CD, rollback, environment consistency        │
├─────────────────┼───────────────────────────────────────────────┤
│ Cost            │ Development, operations, licensing              │
└─────────────────┴───────────────────────────────────────────────┘

Read the full file on GitHub · 356 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 · 356 lines · 0 tokens per session scan A be40bc9c8dff

Subscribe to this mod's changes

architecture-advisor is an agent published in the GitHub repository learnwy/skills (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,737 tokens. 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.