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/jaguarjack/catch-admin/01-parse-tablenpx skills add JaguarJack/catch-admin --skill 01-parse-tablegit clone --depth 1 https://github.com/JaguarJack/catch-adminWhat 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 | $0.00027 | $0.00741 |
| Opus 5 | $0.00014 | $0.00370 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
parse-table 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.
What it actually says
Step 1: Parse Table Definition
从用户输入的表定义中提取关键信息。
Input Format
Table: products
Fields:
- id (primary key)
- name (string, 100, required)
- category_id (foreign key -> categories)
- description (text, nullable)
- price (decimal 10,2, required)
- stock (integer, default 0)
- status (tinyint, default 1)
输入容错与默认推断
- 允许使用以下别名：
Table/表名/表，Module/模块，Model/模型，Fields/字段。 - 允许省略
Fields:标题，仅用-列表表示字段。 - 若只提供
table，则按命名规则推断{Module}与{Model}。 - 若用户显式提供
Module/Model，优先使用用户输入（覆盖推断）。 - 缺少
table时必须先向用户确认，不进行推断生成。
字段解析补充
required表示nullable = false，nullable表示可空；两者都未出现时默认不可空。- 支持别名：
int/integer、bool/boolean、pk/primary key、fk/foreign key。 foreign key -> xxx解析为foreignKey类型，默认index()。
冲突处理优先级
- 用户显式指定（Module/Model/table/字段规则）
- 规则推断（命名规则与默认字段规则）
- 兜底：要求用户澄清后再继续
Output Variables
| Variable | Rule | Example |
|---|---|---|
{table} |
snake_case plural | products |
{Model} |
PascalCase singular | Product |
{Module} |
PascalCase | Product |
{module} |
snake_case | product |
{resources} |
kebab-case plural | products |
{resource} |
kebab-case singular | product |
Field Type Parsing
| Input | Type | Length | Required | Default | FK Target |
|---|---|---|---|---|---|
string, 100 |
string | 100 | no | null | - |
string, 100, required |
string | 100 | yes | null | - |
integer, default 0 |
integer | - | no | 0 | - |
foreign key -> categories |
foreignKey | - | no | 0 | categories |
decimal 10,2 |
decimal | 10,2 | no | null | - |
tinyint, default 1 |
tinyint | - | no | 1 | - |
text, nullable |
text | - | no | null | - |
Naming Conventions
- Module: 通常与 Model 同名，除非用户明确指定
- Table: 复数形式 (products, order_items)
- Model: 单数形式 (Product, OrderItem)
- Route: kebab-case (products, order-items)
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 · 73 lines · 27 tokens per session scan A 84903bce97b8
parse-table is a skill published in the GitHub repository JaguarJack/catch-admin (928 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 741 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 2026-08-30.
Other skills, from other repositories
owl-admin-app-dev
Use this skill when developing an application that installed slowlyo/owl-admin, especially backend CRUD, menus, permissions, controllers, services, routes, config/admin.php, app/Admin, helper functions, settings(), adminpages(), AdminPipeline, upload/file preview issues, route conflicts, custom login/menu examples, or…
owl-admin-devtools-generator
Use this skill for Owl Admin development tools, code generator, dynamic API templates, relationships, visual pages, generated CRUD code, app/ApiTemplates, Support/Apis, Support/CodeGenerator, Controllers/DevTools, or questions about “代码生成器”, “动态 API”, “API 模板”, “关系管理”, “可视化页面”, and “生成 CRUD”.
owl-admin-frontend-assets
Use this skill for Owl Admin frontend assets, admin-views, public/admin-assets, resource publishing, custom React frontend work, amis-editor frontend, layout/theme frontend files, pnpm commands, or questions about “前端资源”, “admin-views”, “自定义前端”, “发布 assets”, “前端源码”, and “打包后台前端”.
owl-admin-ops-commands
Use this skill for Owl Admin installation, publishing assets, upgrades, diagnostics, database inspection, menu maintenance, user creation, password reset, route generation, IDE helper, admin:publish, admin:install, admin:update, admin:doctor, admin:db, admin:menu, admin:create-user, or deployment troubleshooting.
owl-admin-amis-page
Use this skill for Owl Admin pages built with amis, including CRUD pages, forms, tables, detail pages, filters, toolbar actions, iframe pages, custom page schemas, and renderer usage. Trigger when the user mentions amis, schema, Renderers, 后台页面, 列表, 表单, 详情, 筛选, 操作按钮, or admin:make-page.
owl-admin-extension-module
Use this skill for Owl Admin extensions, modules, multi-admin setup, extension service providers, module routes, module config, menus, permissions, admin-module:init, or extensions under the configured extension directory. Trigger on 扩展, 插件, 多模块, module, extension, ServiceProvider, 菜单导入, or 模块后台.