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 agentmods add skills/softtor/nestjs-hexagonal/create-subdomainnpx skills add Softtor/nestjs-hexagonal --skill create-subdomaingit clone --depth 1 https://github.com/Softtor/nestjs-hexagonalWhat 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 | $0.00078 | $0.01845 |
| Opus 5 | $0.00039 | $0.00923 |
| Sonnet 5 | $0.00016 | $0.00369 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
create-subdomain 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-subdomain
Orchestrator that dispatches specialized agents per architectural layer. Each agent loads its corresponding skill and follows TDD.
Agent Dispatch: The dispatch blocks below are conceptual templates. In Claude Code, dispatch agents using the
Agenttool with apromptstring that includes "Load skill nestjs-hexagonal: for patterns." The agent's model and tools are defined in the agent.mdfile frontmatter, not in the tool call.
Compatible with GSD: each phase maps to a GSD execution step.
Phase 1 — Requirements Gathering (inline)
Ask the user via AskUserQuestion. Collect all answers before dispatching agents.
- Bounded context name and business purpose?
- Main entities? Which is the aggregate root?
- Value objects needed? (money, status, email, document, etc.)
- Domain events? (created, updated, status-changed, cancelled)
- Multi-tenant? Field name? (
organizationIdorcompanyId) - CQRS pattern? (A: plain UseCase, B: Command/Query, C: Handler as Orchestrator)
- RBAC guards on endpoints?
- Sub-modules? (e.g., subscription -> plans, payments, core)
- Cross-module ports needed? (which existing modules to communicate with)
- Read model projection in Redis? (CQRS R/W separation)
After answers, create the directory structure:
<context>/
├── domain/
│ ├── entities/__tests__/
│ ├── value-objects/__tests__/
│ ├── events/
│ ├── repositories/
│ ├── services/
│ └── testing/helpers/
├── application/
│ ├── dtos/
│ ├── commands/ # Pattern B/C
│ ├── queries/ # Pattern B/C
│ ├── usecases/ # Pattern A/C
│ └── ports/
└── infrastructure/
├── <context>.module.ts
├── controllers/dtos/
├── database/prisma/repositories/
├── database/prisma/models/
├── database/in-memory/repositories/
├── adapters/
└── listeners/
Phase 2 — Domain Layer via domain-agent (Claude Opus 5)
Dispatch the domain-agent with context from Phase 1:
Agent tool:
subagent_type: "nestjs-hexagonal:domain-agent"
model: claude-opus-5
prompt: |
Create domain layer for "<context>" at "<path>".
Entity: <name>, Props: <list>
VOs: <list>, Events: <list>
Multi-tenant: <field>
TDD: tests first. Load skill nestjs-hexagonal:domain.
What ships with it
3 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.
- 2d ago First seen · 227 lines · 78 tokens per session scan A 3eaa439383d5
create-subdomain is a skill published in the GitHub repository Softtor/nestjs-hexagonal (5 stars, last pushed 22d ago), licensed MIT. It adds 78 tokens to every session and 1,845 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 2026-08-31.
Other skills, from other repositories
design-patterns
Full-spectrum Design Patterns skill: Detect anti-patterns in existing codebases, diagnose architectural debt, propose optimal patterns (GoF, SOLID, DDD, CQRS, Microservices, Cloud), and generate production-ready boilerplate code. Optimized for Next.js, FastAPI, NestJS, Django, Express, and Go.
clean-architecture
Implement Clean Architecture combined with CQRS for scalable NestJS applications.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
frontend-conventions
Frontend convention reference (SvelteKit / Svelte 5). Auto-injected into frontend-aware agents - not user-invocable.