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 skills add martinholovsky/SOTA-skills --skill sota-architecturegit clone --depth 1 https://github.com/martinholovsky/SOTA-skillsWrote 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/martinholovsky/sota-skills/sota-architecture)<a href="https://agentmods.dev/skills/martinholovsky/sota-skills/sota-architecture"><img src="https://agentmods.dev/badge/skills/martinholovsky/sota-skills/sota-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/martinholovsky/sota-skills/sota-architecture"><img src="https://agentmods.dev/badge/skills/martinholovsky/sota-skills/sota-architecture.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00220 | $0.02697 |
| Opus 5.5 | $0.00088 | $0.01079 |
| Sonnet 5.5 | $0.00044 | $0.00539 |
| Haiku 4.5 | $0.00022 | $0.00270 |
Grade A, and why
sota-architecture 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 yesterday.
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.
The source is not reproduced here
Licensed CC-BY-4.0
The repository is licensed CC-BY-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- rules/01-architecture-styles-and-decisions.md 25 KB
- rules/02-domain-modeling-and-boundaries.md 21 KB
- rules/03-distributed-systems-and-events.md 32 KB
- rules/04-resilience-and-failure-design.md 20 KB
- rules/05-scalability-state-and-data.md 18 KB
- rules/06-cloud-native-config-and-delivery.md 17 KB
- rules/07-anti-patterns-catalog.md 13 KB
- rules/08-nats-jetstream.md 25 KB
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.
- yesterday Changed d878c90caa3c
- 2d ago Changed 5eddbef88e27
- 3d ago Changed · +2 lines 02a8cd736087
- 15d ago Changed d2fc5154cf62
- 19d ago Changed 45654648f5d3
- 1mo ago Changed e65a22c75822
- 1mo ago First seen · 116 lines · 220 tokens per session scan A 189e0fa8a150
sota-architecture is a skill published in the GitHub repository martinholovsky/SOTA-skills (23 stars, last pushed today), licensed CC-BY-4.0. It adds 220 tokens to every session and 2,697 once invoked, about $0.0009 per session on Opus 5.5. 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 skills, from other repositories
add-handler
Scaffold a new HTTP handler with service function, store method (if needed), and table-driven test, following the project's internal/{api,service,store} layout. Invoke when the user asks to add an endpoint, handler, or route.
api-endpoint
Scaffold a new API endpoint with request/response Pydantic schemas, service function, route handler, and a pytest test — following the project's layered layout. Invoke when the user asks to add an endpoint, route, or API method.
add-endpoint
Scaffold a new HTTP endpoint across the project's handler, service, and repository layers with tests, following the existing layering. Invoke when the user asks to add a route, endpoint, or API method to a Rust service.
backend
Backend development patterns for services, error handling, logging, caching. Use when building backend services, APIs, or microservices.
api
RESTful API design patterns and best practices. Use when creating endpoints, designing APIs, or implementing routes.
api-design-reviewer
Use when reviewing a PR that adds or changes API endpoints, auditing an existing API for v2 migration, or establishing REST API standards — HTTP semantics, status codes, RFC 9457 problem-details errors, breaking-change detection, pagination, idempotency and concurrency control. Triggers on "API review", "REST design…