aio-architect-reference

aio-architect-reference is a skill for Claude Code, Codex from aiocean/claude-plugins. It costs 33 tokens per session (1,146 once invoked), scanned A, original, MIT.

A reference tool for finding software-architecture patterns and concepts through semantic search, then reading and comparing the relevant articles.

In plain words
What is it for?
It supports looking up patterns, reading full reference articles, comparing approaches, and browsing the available material by volume.
Why use it?
It helps locate suitable architecture ideas without relying only on exact keyword searches or memory.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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

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 skills/aiocean/claude-plugins/aio-architect-reference
Any agent
npx skills add aiocean/claude-plugins --skill aio-architect-reference
Clone the repo
git clone --depth 1 https://github.com/aiocean/claude-plugins

Made for: Claude Code, Codex.

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-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-architect-reference.svg)](https://agentmods.dev/skills/aiocean/claude-plugins/aio-architect-reference)
Your own site
<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-architect-reference"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-architect-reference.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 1,146 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00033 $0.01146
Opus 5 $0.00016 $0.00573
Sonnet 5 $0.00007 $0.00229
Haiku 4.5 $0.00003 $0.00115

Measured 3d ago against content hash 302fe23dadb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aio-architect-reference 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 3d 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-reference/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Architecture Reference

An encyclopedia of 137 in-depth architecture articles. Each article is 3,000-5,000 words covering the problem, core concept, real-world practices (Google, AWS, Microsoft), implementation guidance, trade-offs, common mistakes, and connections to other patterns.

Scripts

SA="${CLAUDE_PLUGIN_ROOT}/scripts"

Commands

Search — Find patterns by meaning

npx tsx "$SA/search-patterns.ts" "<natural language query>" --top 5 --json

Examples:

  • "how to handle database failures gracefully"
  • "scaling read-heavy workloads"
  • "breaking apart a legacy system"
  • "ensuring data consistency across services"

The search uses semantic embeddings — it understands meaning, not just keywords.

List — Browse the catalog

bash "$SA/list-patterns.sh"                      # All 137 patterns by volume
bash "$SA/list-patterns.sh" --volume 4           # Volume 4: Resilience
bash "$SA/list-patterns.sh" --search "event"     # Keyword filter
bash "$SA/list-patterns.sh" --count              # Quick count

Read — Full article

After finding a pattern via search or list, read the full article:

${CLAUDE_PLUGIN_ROOT}/volume-NN-name/pattern-name.md

Always read the full article. These are not summaries — they are comprehensive guides with real-world examples, implementation details, and trade-off analysis.

Compare — Side by side

bash "$SA/compare-patterns.sh" "circuit-breaker" "bulkhead"
bash "$SA/compare-patterns.sh" "microservices" "modular-monolith" "service-based"

Related — Find connected patterns

After reading an article, check its "Connections" section for related patterns. Then read those for a complete picture.

Common pattern clusters:

  • Resilience stack: circuit-breaker + bulkhead + timeout-patterns + retry + load-shedding
  • Event-driven stack: event-driven + event-sourcing + cqrs + publisher-subscriber + saga
  • DDD stack: bounded-context + aggregates + domain-events + context-mapping + ubiquitous-language
  • API stack: resource-oriented-design + api-versioning + api-idempotency + consumer-driven-contracts
  • Scale stack: sharding + partitioning + cache-aside + competing-consumers + materialized-view
  • Operations stack: sre-principles + slo-sli-sla + observability + safe-deployments + chaos-engineering
  • Modern stack: modular-monolith + hexagonal + vertical-slice + architecture-decision-records + fitness-functions

Read the full file on GitHub · 96 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. 3d ago First seen · 96 lines · 33 tokens per session scan A 302fe23dadb4

Subscribe to this mod's changes

aio-architect-reference is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,146 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.