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-project-structuregit 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-project-structure)<a href="https://agentmods.dev/skills/maksimzayats/specx/specx-project-structure"><img src="https://agentmods.dev/badge/skills/maksimzayats/specx/specx-project-structure.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01369 |
| Opus 5 | $0.00037 | $0.00685 |
| Sonnet 5 | $0.00015 | $0.00274 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
specx-project-structure 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 9d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specx Project Structure
Use this skill to create the repo shell and first runnable vertical slice. For
details, read references/blueprint.md.
Workflow
- For a fresh framework-neutral repo, start with
specx init <path>. It creates packaging, strict tooling, rootAGENTS.md, a smallcore/healthuse case and pure service,ioc/container.py, and mirrored unit tests. It intentionally omits delivery and infrastructure; add those packages only with real technology-specific behavior. - Preserve an existing import package declared by the repo. For a new repo,
derive a lowercase underscore name, normalize every non-identifier
character, and verify
name.isidentifier()andnot keyword.iskeyword(name); distribution names and import packages need not be identical. If normalization still yields a keyword or leading digit, choose an explicit valid package name rather than emitting it unchanged. - Create
src/<package>/andtests/packages with empty__init__.pyfiles only. - Add
specxas a runtime dependency and import base classes fromspecx.core.foundation,specx.delivery.foundation, orspecx.infrastructure.foundation. - Use
core/<scope>/as the main boundary. Put application packages at the scope root:capabilities/,dtos/,entities/,exceptions/,gateways/,repositories/,services/, anduse_cases/. Put scope-owned technical adapters underinfrastructure/only when real IO exists. - Add top-level
delivery/for runnable framework apps, lifecycles, controllers, request/response schemas, and delivery-only services. - Add top-level
infrastructure/for shared technical resources such as SQLAlchemy session factories, logging, telemetry, and external client factories. App-owned pooled clients live here even when only one scope currently consumes them; bounded short-lived clients may stay with the scope adapter. - Add
infrastructure/logging/with a stdlibLoggingConfiguratorandLoggingSettingsfor every new API repo. - Add
ioc/fordiwire.Containercreation and explicit bindings. - Add
shared/only for stable cross-scope application primitives such as unit-of-work contracts, clocks, ids, or errors. - Add
migrations/with Alembic when SQLAlchemy models exist. - Build the first user-requested business vertical slice. The initializer's
process-health slice is a framework-neutral composition example, not a
readiness check. With a delivery framework, map or replace it deliberately:
keep simple liveness at delivery, and use
core/healthfor/readyzwhen readiness checks a required dependency or policy is shared across deliveries. - Create root
AGENTS.mdfor every new repo. Include runnable project commands from$specx-project-toolingand specx boundaries from$specx-component-architecture. - Do not create an empty local
foundation/package. Createsrc/<package>/foundation/only for a real project-local base category or a stateful framework base that must not be shared globally, such as a SQLAlchemy declarative base. - Add tests only where there is real code to test. Do not create empty folders just to satisfy the diagram.
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.
- 9d ago First seen · 101 lines · 75 tokens per session scan A 810eed68e684
specx-project-structure is a skill published in the GitHub repository maksimzayats/specx (201 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,369 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
scaffold-archipy-domain
Scaffold a full ArchiPy domain slice (DTOs, errors, repository adapters, logic, service). Use when adding a new domain to an existing ArchiPy app.
scaffold-archipy-app
Scaffold a minimal ArchiPy application package (config, containers stub, domain slice, helpers tree, optional manage.py). Use when starting a new ArchiPy-based service or asking to bootstrap project layout.
scaffold-archipy-logic
Scaffold an ArchiPy logic class with unit-of-work decorator and domain DTO I/O. Use when adding a use-case under logics/{domain}/.
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…
software-engineer-python
Auto-route to this skill if project contains.
python
Enforces FastAPI, Dependency Injection, and general Python coding standards based on the repository structure.