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 maksimzayats/specx --skill specx-add-infrastructure-adaptergit clone --depth 1 https://github.com/maksimzayats/specxWrote 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/maksimzayats/specx/specx-add-infrastructure-adapter)<a href="https://agentmods.dev/skills/maksimzayats/specx/specx-add-infrastructure-adapter"><img src="https://agentmods.dev/badge/skills/maksimzayats/specx/specx-add-infrastructure-adapter/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/maksimzayats/specx/specx-add-infrastructure-adapter"><img src="https://agentmods.dev/badge/skills/maksimzayats/specx/specx-add-infrastructure-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.00840 |
| Opus 5 | $0.00038 | $0.00420 |
| Sonnet 5 | $0.00015 | $0.00168 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
specx-add-infrastructure-adapter 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 12d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specx Add Infrastructure Adapter
Use this skill whenever code talks to external systems. Read
references/adapter.md before writing adapters.
Workflow
- Define or reuse a repository under
repositories/for owned persistence. Repository ports inheritBaseRepositoryand mark required methods with@abstractmethod. - Define or reuse a gateway under
gateways/for outbound business capabilities to external systems such as OpenAI, payments, email, queues, or external HTTP APIs. Gateway ports inheritBaseGateway, mark required methods with@abstractmethod, declare external effects, and do not return entities. - Put concrete implementations under
core/<scope>/infrastructure/<technology>/. - Inject external clients, session factories, Redis clients, SDK clients, or
project-owned client factories. Do not hide client construction inside
business methods. Generated HTTP adapters use
httpx2, imported from thehttpx2namespace; do not generate new legacyhttpximports. - A bounded short-lived client factory may stay beside its scope adapter. Put
every app-owned pooled client factory or wrapper under top-level
infrastructure/<technology>/, even with only one current consumer. - Give long-lived app-owned infrastructure resources an explicit async
close()method; FastAPI lifecycle owns calling it on shutdown. - Keep technical query/request code in infrastructure.
- Repositories may return entities. Gateways must not return entities; return DTOs, primitives, enums, or explicit result objects. Do not return ORM models or SDK response objects to core.
- Translate low-level exceptions into core exceptions only when callers need to handle them. Catch narrow driver or SDK exceptions, preserve the cause, and never expose raw provider messages, SQL, parameters, bodies, or URLs.
- For transactional persistence, implement an active
UnitOfWorkand aUnitOfWorkManager; register the manager, not repositories, active UoWs, or UoW providers for use-case injection. - Register adapter bindings in private
_register_dependencies(...)insideioc/container.py. Register every technical resource once at its owner boundary and close that same app-scoped instance from lifecycle. - Add focused integration tests only when the adapter has meaningful project-owned behavior to protect; do not add generic CRUD or upstream library tests just because an adapter file exists.
- For SQLAlchemy adapters, add or update Alembic migrations with
$specx-sqlalchemy-migrations.
What ships with it
2 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.
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.
- 12d ago First seen · 73 lines · 76 tokens per session scan A d9146b3fb159
specx-add-infrastructure-adapter is a skill published in the GitHub repository maksimzayats/specx (201 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 840 once invoked, about $0.0004 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 skills, from other repositories
using-redis-token-buckets
Use when adding a bucket-like rate limit backed by Redis: a per-caller budget with burst capacity and continuous refill, a refund path for requests that did no work, or a limit whose Retry-After must be a real wait rather than a window edge. posthog/tokenbucket.py provides an atomic Lua token bucket (consume, refund…
spring-boot-cache
Provides patterns for implementing Spring Boot caching: configures Redis/Caffeine/EhCache providers with TTL and eviction policies, applies @Cacheable/@CacheEvict/@CachePut annotations, validates cache hit/miss behavior, and exposes metrics via Actuator. Use when adding caching to Spring Boot services, configuring…
using-redis-token-buckets
Use when adding a bucket-like rate limit backed by Redis: a per-caller budget with burst capacity and continuous refill, a refund path for requests that did no work, or a limit whose Retry-After must be a real wait rather than a window edge. posthog/tokenbucket.py provides an atomic Lua token bucket (consume, refund…
spring-data-redis
Use when implementing caching, session storage, rate limiting, or any Redis integration. Covers cache-aside pattern, key naming, TTL strategy, and serialization config.
background-job-orchestrator
Expert in background job processing with Bull/BullMQ (Redis), Celery, and cloud queues. Implements retries, scheduling, priority queues, and worker management. Use for async task processing, email campaigns, report generation, batch operations. Activate on "background job", "async task", "queue", "worker", "BullMQ"…
nw-sd-patterns
Core distributed systems patterns - load balancing, caching, sharding, consistent hashing, message queues, rate limiting, CDN, Bloom filters, ID generation, replication, conflict resolution, CAP theorem.