spec-infra

A specialist subagent that reviews infrastructure, security, and non-functional requirements in technical specifications. It is designed to be called by a specification-review command, not directly.

In plain words
What is it for?
Use it as part of a specification review to examine authentication, authorisation, encryption, privacy, common web risks, monitoring, scalability, performance, and CI/CD requirements.
Why use it?
It helps expose missing or unclear concerns about deployment, access control, data protection, monitoring, scaling, performance, and delivery pipelines before implementation.

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/dapi/claude-code-marketplace/spec-infra
Clone the repo
git clone --depth 1 https://github.com/dapi/claude-code-marketplace
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,290 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 $0.00061 $0.02290
Opus 5 $0.00030 $0.01145
Sonnet 5 $0.00012 $0.00458
Haiku 4.5 $0.00006 $0.00229

Measured 2d ago against content hash 906073f31fa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-infra 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.

spec-reviewer/agents/spec-infra.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Infrastructure Agent

Субагент для анализа инфраструктуры, безопасности и NFR в спецификациях и ТЗ. Выполняет роль DevOps/Security/SRE Architect.

Входные данные

Получает текст спецификации от оркестратора через prompt.

Задача

Проанализировать всё, что связано с инфраструктурой, безопасностью и нефункциональными требованиями.


Чеклист анализа

Безопасность

Аутентификация
  • Auth механизм — JWT, OAuth2, Session, API keys?
  • Token lifetime — время жизни токенов?
  • Refresh strategy — как обновлять токены?
  • MFA — нужна ли многофакторная аутентификация?
  • Password policy — требования к паролям?
Авторизация
  • RBAC/ABAC — модель контроля доступа?
  • Роли — какие роли и их права?
  • Permissions — гранулярность прав?
  • Resource ownership — кто владелец ресурсов?
Защита данных
  • Encryption at rest — шифрование хранимых данных?
  • Encryption in transit — TLS/HTTPS?
  • PII handling — как обрабатывать персональные данные?
  • Data masking — маскировка в логах?
  • GDPR/compliance — соответствие регуляциям?
OWASP Top 10
  • Injection — защита от SQL/NoSQL/Command injection?
  • XSS — защита от cross-site scripting?
  • CSRF — защита от cross-site request forgery?
  • Rate limiting — защита от brute force?
  • Input validation — валидация всех входных данных?

Производительность (NFR)

  • Latency — требования к времени отклика (p50, p95, p99)?
  • Throughput — требуемая пропускная способность (RPS)?
  • Concurrent users — сколько одновременных пользователей?
  • Data volume — объёмы данных для обработки?
  • Peak load — пиковые нагрузки и как их обрабатывать?

Масштабируемость

  • Horizontal scaling — можно ли масштабировать горизонтально?
  • Stateless design — сервисы stateless?
  • Database scaling — read replicas, sharding?
  • Caching strategy — стратегия кэширования?
  • Queue/async processing — очереди для тяжёлых операций?

Read the full file on GitHub · 249 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 · 249 lines · 61 tokens per session scan A 906073f31fa4

Subscribe to this mod's changes

spec-infra is an agent published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 2,290 once invoked, about $0.0003 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.