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/artisancloud/powerx/modelnpx skills add ArtisanCloud/PowerX --skill modelgit clone --depth 1 https://github.com/ArtisanCloud/PowerXWrote 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/artisancloud/powerx/model)<a href="https://agentmods.dev/skills/artisancloud/powerx/model"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/model.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00024 | $0.01647 |
| Opus 5 | $0.00012 | $0.00823 |
| Sonnet 5 | $0.00005 | $0.00329 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
crud-model scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerX CRUD Model
步骤
- 打开
本文件内嵌规则。 - 按规则执行实现/校对。
- 完成后按核对清单验收。
核对点
- 与 PowerX 当前代码结构、路径与命名一致。
- 仅在传输层/契约层做职责内改动,不跨层越界。
规则(内嵌)
model.yaml
kind: ruleset
name: crud_model
version: 1.0.0
owner: powerx
status: stable
meta:
intent: >
统一 GORM 模型约束(多租户、软删、表名、索引/唯一、JSONB、状态字段),
以及迁移注册与目录放置的硬性规则,确保与 Repository/Service 分层契合。
references:
- constitution.md
- dev_crud_http_guides.md
scope:
codebase:
model_dir: "pkg/corex/db/persistence/model"
migrate_entry:
- "cmd/database/migrate.go" # 总入口(集中触发)
module_migrate_globs:
- "internal/server/**/persistence/migrate.go" # 模块内注册器(分散声明)
principles:
- 模型必须嵌入 PowerModel 或 PowerUUIDModel;包含 DeletedAt 与 TenantID 字段。 # :contentReference[oaicite:21]{index=21}
- 表名必须显式返回 `${schema}.${table}`,schema 由 PowerXSchema 控制。 # :contentReference[oaicite:22]{index=22}
- 索引/唯一约束通过 GORM Tag 声明;JSON 字段统一使用 datatypes.JSON(JSONB)。 # :contentReference[oaicite:23]{index=23}
- 状态字段统一命名 Status,默认值 1;禁止散落 SQL 文件,迁移统一走 AutoMigrate。 # :contentReference[oaicite:24]{index=24}
- 模型源码文件需以 `_gorm.go` 结尾,保持与现有目录命名一致,便于一眼识别 GORM 实体。
- 非持久化结构体(DTO/辅助类型)禁止携带 `gorm:""` Tag,避免误导迁移与仓储逻辑。
- PowerX 核心模块的模型必须集中在 `pkg/corex/db/database/migration.go::MigrateCoreModels` 注册;独立 Server(如 Agent)可在自身 `internal/server/<module>/persistence/migrate.go` 中维护迁移函数。
checks:
directories:
- id: model.path
level: error
when:
glob: "pkg/corex/db/persistence/model/**/**.go"
assert:
- must_package_suffix: "model"
embedding_and_fields:
- id: base_model.embedded
level: error
when:
glob: "pkg/corex/db/persistence/model/**/**.go"
assert:
- must_embed_one_of: ["model.PowerModel","model.PowerUUIDModel"]
- must_have_fields:
- "TenantID uint64 `gorm:\"index;not null\"`"
- "DeletedAt gorm.DeletedAt `gorm:\"index\"`"
- should_have_fields:
- "Status int16 `gorm:\"default:1;index\"`"
table_naming:
- id: table.name.func
level: error
when:
glob: "pkg/corex/db/persistence/model/**/**.go"
assert:
- must_define: "func (*).TableName() string"
- must_return_schema_const: "model.PowerXSchema" # 返回 schema.table
json_and_index:
- id: jsonb.tag
level: warn
when:
contains: "datatypes.JSON"
assert:
- must_have_tag: "gorm:\"type:jsonb\""
- id: unique_and_index_tags
level: warn
when:
glob: "pkg/corex/db/persistence/model/**/**.go"
assert:
- recommend_tags: ["uniqueIndex","index"]
migration_registration:
- id: migrate.fn.exists
level: error
when:
glob: "internal/**/migration.go"
assert:
- must_define_like: "func Migrate*Models(db *gorm.DB) error" # 模块自迁移注册 # :contentReference[oaicite:25]{index=25}
- id: migrate.entry.calls
level: warn
when:
file: "cmd/database/migrate.go"
assert:
- must_call: "Migrate*Models("
acceptance:
checklist:
- "[ ] 模型嵌入 PowerModel/PowerUUIDModel,并含 TenantID/DeletedAt/Status" # :contentReference[oaicite:26]{index=26}
- "[ ] 表名返回 ${schema}.${table},表名常量集中到 tables.go"
- "[ ] JSON 字段使用 datatypes.JSON + jsonb"
- "[ ] 唯一约束/复合索引通过 Tag 声明"
- "[ ] 迁移函数 Migrate<Module>Models 已实现并在入口注册(核心模块写入 MigrateCoreModels,独立 Server 写入各自 migrate.go)" # :contentReference[oaicite:27]{index=27}
- "[ ] 不交付 .sql,统一 AutoMigrate + 运行期校验"
- "[ ] 文件命名采用 *_gorm.go,与 GORM 模型约定保持一致"
templates:
model_go: |
package {{domain}}model
import (
"time"
"gorm.io/gorm"
"gorm.io/datatypes"
"github.com/ArtisanCloud/PowerX/pkg/corex/db/persistence/model"
)
const Table{{Entity}} = "{{$table}}"
type {{Entity}} struct {
model.PowerUUIDModel
TenantID uint64 `gorm:"index;not null"`
Name string `gorm:"type:varchar(128);index"`
Code string `gorm:"type:varchar(64);uniqueIndex:uk_{{table}}_tenant_code"`
Meta datatypes.JSON `gorm:"type:jsonb;default:'{}'"`
Status int16 `gorm:"default:1;index"`
CreatedAt time.Time
UpdatedAt time.Time
DeletedAt gorm.DeletedAt `gorm:"index"`
}
func (*{{Entity}}) TableName() string {
return model.PowerXSchema + "." + Table{{Entity}}
}
migrate_go: |
package {{domain}}migration
import (
"gorm.io/gorm"
dbm "{{module_path}}/pkg/corex/db/persistence/model/{{domain}}"
)
func Migrate{{Module}}Models(db *gorm.DB) error {
if err := db.AutoMigrate(
&dbm.{{Entity}}{},
); err != nil {
return err
}
// 可选:运行期校验索引/约束
// if !db.Migrator().HasIndex(&dbm.{{Entity}}{}, "uk_{{table}}_tenant_code") { ... }
return nil
}
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.
- today First seen · 172 lines · 24 tokens per session scan A 456904e3a774
crud-model is a skill published in the GitHub repository ArtisanCloud/PowerX (364 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,647 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
om-judge-agent-session
Judge generated Open Mercato code from a standalone harness eval or a user-shared agent session bundle. Use for LLM-as-judge validation, generative eval review, session/artifact analysis, harness-quality diagnosis, "judge this session", "analyze this eval", or "oceń sesję/agenta"; checks fixed validation evidence…
om-app-spec-writing
Write and review a business-level App Spec — domain model, workflows with ROI, user stories with failure paths, platform gap analysis in atomic commits, and a phased rollout — BEFORE any feature spec or code exists. One level above om-spec-writing, which decomposes the finished App Spec into feature specs. Use when…
WRITE_ATTACHMENT_SERVICE
You are adding an inbound/attachment module to a domain crate. This module implements the attachment::AttachmentService trait so the crate can resolve its entity IDs into AI-consumable attachment content.
ai-sdk-development
TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK. Activate when building, editing AI agents, chatbots, text generation, image generation, audio/TTS, transcription/STT, embeddings, RAG, vector stores, reranking, structured output, streaming, conversation memory, tools, queueing…
skmtc-lang-kotlin
The Kotlin target-language layer for Skmtc generators (@skmtc/lang-kotlin): base factories, KtSnippet, the seven entity kinds, packages-from-paths imports, the head+value render model, KtAnnotation and the composition classes, sanitization and @SerialName placement, plus the current-API worked example (the shipped…
skmtc-generator
Author and edit Skmtc generators — packages that project an OpenAPI domain model into application code. Method: clone the nearest stock generator, then apply the engine rules imitation can't teach. Assumes zero prior Skmtc knowledge. Use when asked to "write a skmtc generator", "author/clone/customize gen-x", "add a…