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.
npx agentmods add agents/rand/cc-polymath/architecture-advisorgit clone --depth 1 https://github.com/rand/cc-polymathWhat 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 | $0.00035 | $0.00731 |
| Opus 5 | $0.00017 | $0.00365 |
| Sonnet 5 | $0.00007 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
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.
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
Recommended Skills to Load
Based on the architecture problem, load relevant gateway skills:
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.
- 2d ago First seen · 103 lines · 35 tokens per session scan A 4d794debb6d9
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.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
comparator
Compare two outputs WITHOUT knowing which skill version produced them.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.