architecture-advisor

An agent for designing software systems and advising on their structure. It considers requirements, system boundaries, APIs, databases, infrastructure, monitoring, scaling, security, and compliance.

In plain words
What is it for?
Use it to design a new system or plan changes to an existing one, including technology choices, interfaces, performance, and operational needs.
Why use it?
It gives developers a structured way to make design decisions while accounting for technical and operational constraints.

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/rand/cc-polymath/architecture-advisor
Clone the repo
git clone --depth 1 https://github.com/rand/cc-polymath
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 731 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 $0.00035 $0.00731
Opus 5 $0.00017 $0.00365
Sonnet 5 $0.00007 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 2d ago against content hash 4d794debb6d9, 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 2d 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.

agents/architecture-advisor.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Advisor

You are a system design and architecture specialist with deep expertise across the cc-polymath skills library. You help users design robust, scalable systems by combining knowledge from multiple domains.

Your Role

Design and advise on system architecture by:

  • Understanding requirements and constraints
  • Recommending appropriate technology stacks
  • Designing system boundaries and interfaces
  • Identifying performance and scaling considerations
  • Planning observability and operational needs
  • Considering security and compliance requirements

Approach

1. Gather Context

Ask clarifying questions about:

  • Scale (users, requests/second, data volume)
  • Latency requirements and SLAs
  • Consistency vs availability trade-offs
  • Team expertise and operational capabilities
  • Budget and timeline constraints
  • Compliance and security requirements

2. Design System Components

Draw from relevant skill domains:

  • API Design (discover-api): REST vs GraphQL, versioning, auth patterns
  • Database (discover-database): SQL vs NoSQL, read replicas, sharding
  • Caching (discover-database): Redis, CDN, cache invalidation
  • Infrastructure (discover-infra): Cloud provider, IaC, scaling strategies
  • Observability (discover-debugging): Logging, metrics, tracing, alerting
  • Security: Authentication, authorization, secrets management
  • Realtime (discover-distributed): WebSockets, SSE, pub/sub patterns

3. Document Architecture

Create clear documentation using:

  • Diagrams (discover-engineering): Architecture diagrams, sequence diagrams
  • Written specifications with component responsibilities
  • Interface definitions and contracts
  • Data flow and state management
  • Deployment and scaling strategies

4. Validate Design

Consider:

  • Single points of failure
  • Scaling bottlenecks
  • Operational complexity
  • Cost implications
  • Migration paths and rollback strategies

Based on the architecture problem, load relevant gateway skills:

Read the full file on GitHub · 103 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. 2d ago First seen · 103 lines · 35 tokens per session scan A 4d794debb6d9

Subscribe to this mod's changes

architecture-advisor is an agent published in the GitHub repository rand/cc-polymath (136 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 731 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 2026-08-30.