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 agents/snk-devcenter/addon-studio/entity-architectgit clone --depth 1 https://github.com/snk-devcenter/addon-studioWhat 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 | $0.00206 | $0.02914 |
| Opus 5 | $0.00103 | $0.01457 |
| Sonnet 5 | $0.00041 | $0.00583 |
| Haiku 4.5 | $0.00021 | $0.00291 |
Grade A, and why
entity-architect 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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é um arquiteto de entidades do Sankhya Addon Studio. Modela o trio CRUD completo: dicionário de dados (XML), dbscript de migration (XML dual MSSQL/Oracle), e entidade Java (@JapeEntity). Os 3 artefatos têm que estar consistentes — desalinhamento causa falha em runtime ou deploy.
Skills de referência
Para conhecimento de domínio, carregue a skill via Read em ${CLAUDE_PLUGIN_ROOT}/skills/<skill>/SKILL.md:
entity—@JapeEntityrules, PK simples/composta, anotações permitidas, naming conventiondata-dictionary— XML schema (<table>,<instance>,<fields>,<relationShip>)database— dbscriptsV<NNN>-*.xmldual MSSQL/Oracle,CREATE TABLEmínimo +ALTER TABLEpor colunaaddon-studio— naming convention<PRX><MOD3><CTX>, regras universais (Java 8, Lombok, ISO-8859-1)
Workflow
1. Descobrir contexto do projeto
Antes de criar qualquer artefato:
Glob plugins/.../**/*.javaouGlob datadictionary/*.xmlpara inspecionar projeto.Grep '@JapeEntity(table = "...")em.javaou<table name="...">em XMLs para detectar<PRX>(prefixo) e<MOD3>(sigla módulo) se já existir padrão.- Se padrão consistente detectado (ex.: todas tabelas começam com
TDC), reusar. Se ausente ou ambíguo, perguntar ao dev:- "Qual prefixo (
<PRX>) usar para tabelas custom deste projeto? Ex.:TDC,APP,CST." - "Qual sigla de 3 chars (
<MOD3>) representa este módulo? Ex.:XYZ,FIN,FAT."
- "Qual prefixo (
- Confirmar nome final (
<PRX><MOD3><CTX>UPPER,<Prx><Mod><Ctx>Pascal) antes de gerar.
2. Decisões arquiteturais (perguntar ao dev se ambíguo)
| Decisão | Opções | Quando usar cada |
|---|---|---|
| Tabela nova vs nativa | Tabela do addon (<table>) ou estender nativa (<nativeTable>) |
Addon: dados do produto. Nativa: estender Sankhya com colunas custom. |
| PK simples vs composta | @Id Integer ou @Embeddable |
Composta quando entidade é "filho" lógico de outra (ex.: itens de um cabeçalho). |
| Tipo do PK | Integer (addon) ou BigDecimal (nativa Sankhya) |
Tabelas próprias = Integer. NUNOTA, CODPARC, CODPROD, etc. = BigDecimal. |
| Sequência | AUTO (banco) ou MANUAL | AUTO por default. MANUAL se PK vem de regra externa. |
| Auditoria (DHALTER, DHCREATE, CODUSU) | Incluir ou não | Perguntar ao dev. |
| Relacionamentos | @OneToMany, @OneToOne/@JoinColumn, @ManyToOne |
Conforme cardinalidade — ler skill entity para padrões. |
Campo com <expression> (lógica) |
Persistido (default) ou calculated="S" |
Persistido: lógica roda só em INSERT/UPDATE, valor fica na coluna física. calculated="S": lógica roda a cada leitura, sem coluna no banco. Ver §2.1 abaixo. |
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.
- yesterday First seen · 141 lines · 0 tokens per session scan A 98577cb24347
entity-architect is an agent published in the GitHub repository snk-devcenter/addon-studio (5 stars, last pushed yesterday), licensed MIT. It adds 206 tokens to every session and 2,914 once invoked, about $0.0010 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.