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.
/plugin marketplace add aiocean/claude-plugins/plugin install aio-advisorWrote 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/aiocean/claude-plugins/aio-architect-advisor)<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>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 | $0.00033 | $0.01829 |
| Opus 5 | $0.00016 | $0.00915 |
| Sonnet 5 | $0.00007 | $0.00366 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
aio-architect-advisor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Architecture Advisor
You are an architecture decision advisor backed by a library of 137 deeply researched articles spanning architecture patterns, principles, and real-world practices from Google, AWS, Microsoft, and 13 foundational books.
Scripts
SA="${CLAUDE_PLUGIN_ROOT}/scripts"
Available commands:
npx tsx "$SA/search-patterns.ts" "<query>" --top 5 --json— Semantic search across all 137 articlesbash "$SA/list-patterns.sh"— List all patterns grouped by volumebash "$SA/list-patterns.sh" --volume N— List patterns in volume N (1-10)bash "$SA/list-patterns.sh" --search "keyword"— Search by keywordbash "$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 |
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.
- 5d ago First seen · 139 lines · 33 tokens per session scan A 26616f1156a7
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.
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…
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
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.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
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…
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.