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-core-use-casegit 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-core-use-case)<a href="https://agentmods.dev/skills/maksimzayats/specx/specx-add-core-use-case"><img src="https://agentmods.dev/badge/skills/maksimzayats/specx/specx-add-core-use-case/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-core-use-case"><img src="https://agentmods.dev/badge/skills/maksimzayats/specx/specx-add-core-use-case.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 | $0.00070 | $0.00930 |
| Opus 5.5 | $0.00028 | $0.00372 |
| Sonnet 5.5 | $0.00014 | $0.00186 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
specx-add-core-use-case 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specx Add Core Use Case
Use this skill for one application action at a time. Read
references/use-case.md before writing the use case.
Workflow
- Name the action directly, for example
CreateInvoiceUseCase. - Put it under
core/<scope>/use_cases/<action>.py. - Inherit
BaseUseCasefromspecx.core.foundation.use_case. - Define exactly one same-file input class: a
Commandfor state-changing use cases or aQueryfor read-only use cases. Even empty inputs are explicit. - Make commands inherit
specx.core.foundation.command.BaseCommand, queries inheritspecx.core.foundation.query.BaseQuery, and result DTOs inheritspecx.core.foundation.dto.BaseDTO. Prefer@dataclass(frozen=True, kw_only=True, slots=True)for all of these core data classes unless the user asks for another model type. - Treat commands and queries as input contracts, not DTOs. Do not make
commands or queries inherit
BaseDTO, put them underdtos/, or add aDTOsuffix. execute(...)accepts exactly one keyword-only argument namedcommandorqueryand returns DTOs, not entities.- Inject services, capabilities, gateways, and UoW managers with
Injected[...]. Keep infrastructure/runtime settings out of core use cases; expose required business policy as a typed core value or collaborator. For transactional persistence, inject the scopeUnitOfWorkManagerand open the active unit of work insideexecute(...). Do not inject repositories, SQLAlchemy sessions/engines/session factories, or concrete infrastructure adapters directly into use cases. - Keep framework schemas, routers, ORM models, Redis clients, HTTP clients, and entity return types out of the use case.
- Mark secret-bearing dataclass fields with
field(repr=False)and never log whole commands, queries, or DTOs that may contain sensitive values. - Add or update flat unit tests for the behavior. The test receives the
native pytest
containerfixture, registers local doubles or inline mocks before resolution, and resolves the use case withcontainer.resolve(UseCaseClass). If the use case injects aUnitOfWorkManager, also add a core integration test undertests/integration/core/...against the real persistence graph (and the transactional database graph when database-backed).
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.
- 2mo ago First seen · 79 lines · 70 tokens per session scan A f7d194063610
specx-add-core-use-case is a skill published in the GitHub repository maksimzayats/specx (200 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 930 once invoked, about $0.0003 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
scaffold-utils
Add or wire pure helpers/utils, preferring ArchiPy utils (datetime, JWT, password, file, string). Use for "add a helper/util function", "format dates", "hash passwords", or "generate tokens".
python
Enforces FastAPI, Dependency Injection, and general Python coding standards using uv inside the server directory.
software-engineer-python
Use when implementing or modifying Python applications, services, packages, or tests.
clean-architecture-python
Use when laying out a Python service packaged with pyproject.toml (FastAPI or another web framework), or adding a feature, endpoint, use case, aggregate or repository to one — which package a module belongs in, which package may import which, and how an endpoint reaches a use case. Not for configuration, dependency or…
Python Clean Architecture
This skill should be used when the user asks to "scaffold a FastAPI project", "set up clean architecture", "refactor to clean architecture", "add a new endpoint", "add a router", "add an operation", "add a repository", "review my code structure", "apply design patterns in Python", "decouple my code", "improve code…
py-clean-arch
Use this skill when the user asks about Clean Architecture in Python — not generic theory, but the specific layer conventions (l1entities, l2usecases, l3interfaceadapters, l4frameworksanddrivers), folder patterns, boundary interfaces, and .importlinter.ini contracts from CJHwong/py-clean-architecture-examples. Fetches…