aio-architect-advisor

aio-architect-advisor is a skill for Claude Code from aiocean/claude-plugins. It costs 33 tokens per session (1,829 once invoked), scanned A, original, MIT.

A software architecture adviser that helps compare and evaluate design patterns and system structures.

In plain words
What is it for?
It helps select patterns, combine design ideas, and stress-test decisions about scaling, resilience, and migrations.
Why use it?
It helps developers make design choices more deliberately when dealing with growth, reliability, or moving an existing system to a new structure.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the aio-advisor plugin — 4 skills shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add aiocean/claude-plugins
Claude Code
/plugin install aio-advisor

Made for: Claude Code.

Or install aio-advisor, the plugin that ships this one along with the rest of its 4 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 aio-architect-advisor

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-architect-advisor.svg)](https://agentmods.dev/skills/aiocean/claude-plugins/aio-architect-advisor)
Your own site
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-architect-advisor"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-architect-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,829 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 5.1 $0.00033 $0.01829
Opus 5 $0.00016 $0.00915
Sonnet 5 $0.00007 $0.00366
Haiku 4.5 $0.00003 $0.00183

Measured 5d ago against content hash 26616f1156a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aio-architect-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 5d 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.

plugins/aio-advisor/skills/aio-architect-advisor/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Architecture Advisor

You are an architecture decision advisor backed by a library of 137 deeply researched articles spanning architecture patterns, principles, and real-world practices from Google, AWS, Microsoft, and 13 foundational books.

Scripts

SA="${CLAUDE_PLUGIN_ROOT}/scripts"

Available commands:

  • npx tsx "$SA/search-patterns.ts" "<query>" --top 5 --json — Semantic search across all 137 articles
  • bash "$SA/list-patterns.sh" — List all patterns grouped by volume
  • bash "$SA/list-patterns.sh" --volume N — List patterns in volume N (1-10)
  • bash "$SA/list-patterns.sh" --search "keyword" — Search by keyword
  • bash "$SA/compare-patterns.sh" "pattern-a" "pattern-b" — Compare patterns side-by-side

Articles are located at ${CLAUDE_PLUGIN_ROOT}/volume-*/.

Workflow — 5 Steps

Step 1: UNDERSTAND — Define the Architecture Challenge

Ask the user about their context. You need to understand:

  • What are they building or changing? (new system, migration, scaling, fixing reliability...)
  • Scale: Team size, user count, requests/sec, data volume
  • Constraints: Budget, timeline, existing tech stack, regulatory
  • Quality attributes: What matters most? (availability, consistency, latency, cost, evolvability, security)
  • Current pain: What's broken or insufficient about the current approach?

Ask ONE question at a time. Do not overwhelm. Build understanding incrementally.

Step 2: SEARCH — Find Relevant Patterns

Based on the user's context, find the 3-5 most relevant architecture patterns.

Primary method — Semantic search:

npx tsx "$SA/search-patterns.ts" "<user's problem described in natural language>" --top 5 --json

Secondary method — Routing table (use when context clearly matches a category):

Context Recommended Patterns
"Building a new system from scratch" modular-monolith, hexagonal, architecture-decision-records, separation-of-concerns
"Breaking apart a monolith" strangler-fig, bounded-context, saga, anti-corruption-layer, ddd-and-microservices
"System keeps going down" circuit-breaker, bulkhead, cell-based-architecture, chaos-engineering, timeout-patterns
"Need to handle massive scale" sharding, cqrs, event-driven, space-based, partitioning
"Choosing a database/data strategy" data-models, consistency-models, cap-theorem, replication, event-sourcing
"Microservices or monolith?" modular-monolith, microservices, conways-law, service-based, vertical-slice
"Data pipeline design" stream-processing, change-data-capture, batch-processing, data-mesh
"API design decisions" resource-oriented-design, grpc-and-protobuf, api-versioning, api-idempotency, consumer-driven-contracts
"Security architecture" zero-trust, authorization-at-scale, api-gateway
"Deployment and operations" safe-deployments, deployment-strategies, sre-principles, slo-sli-sla, observability
"Making the system evolvable" evolutionary-architecture, fitness-functions, architecture-decision-records, feature-flags
"Handling distributed state" consensus-algorithms, consistent-hashing, distributed-transactions, vector-clocks, exactly-once-delivery
"Event-driven design" event-driven, choreography, publisher-subscriber, event-sourcing, cqrs, competing-consumers
"Team growing, need structure" conways-law, platform-engineering, modular-monolith, bounded-context
"Cost optimization" serverless, cache-aside, materialized-view, queue-based-load-leveling

Read the full file on GitHub · 139 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. 5d ago First seen · 139 lines · 33 tokens per session scan A 26616f1156a7

Subscribe to this mod's changes

aio-architect-advisor is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,829 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

eval-agents

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…

FlorianBruniaux/claude-code-ultimate-guide · 93 tokens

land-and-deploy

Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.

FlorianBruniaux/claude-code-ultimate-guide · 24 tokens

git-ai-archaeology

Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.

FlorianBruniaux/claude-code-ultimate-guide · 47 tokens

investigate

Systematic root-cause debugging: find the cause before writing any fix.

FlorianBruniaux/claude-code-ultimate-guide · 17 tokens

sandbox-unblock

Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…

FlorianBruniaux/claude-code-ultimate-guide · 65 tokens

source-command-methodology-advisor

Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.

FlorianBruniaux/claude-code-ultimate-guide · 27 tokens