agentmods.dev

autumn: Skill for Cursor

.cursor/skills/autumn-framework-3x/SKILL.md

autumn-framework-3x is a skill for Cursor from henryxm/autumn. It costs 620 tokens per session (7,479 once invoked), scanned A, a copy of autumn-framework-2x, Apache-2.0.

A development guide for the Autumn 3.0.0 software framework, using JDK 17 or newer, Spring Boot 3.5, MyBatis-Plus 3.x, and the jakarta namespace. It applies only to the Autumn 3.0.0 branch or projects locked to that version.

In plain words
What is it for?
Use it when building or reviewing Autumn 3.0.0 applications, including database access, service modules, generated code, pages, and related framework components.
Why use it?
It prevents developers from mixing rules and dependencies from Autumn 3.x with the older 2.x line, which uses a different Java and Spring setup.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

This is henryxm/autumn's own configuration. It tells Cursor how to work on autumn itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autumn configures →

not rated 49repo 15d ago A scan 620 tokens copy · 86% Apache-2.0
View source ↗ henryxm/autumn
Reuse

Borrowing it

Nothing to install: this file belongs to henryxm/autumn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/henryxm/autumn/master/.cursor/skills/autumn-framework-3x/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/henryxm/autumn

Made for: Cursor.

Wrote 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.

agentmods badge for autumn-framework-3x

README.md
[![agentmods](https://agentmods.dev/badge/skills/henryxm/autumn/autumn-framework-3x/github.svg)](https://agentmods.dev/skills/henryxm/autumn/autumn-framework-3x)
Your own site
<a href="https://agentmods.dev/skills/henryxm/autumn/autumn-framework-3x"><img src="https://agentmods.dev/badge/skills/henryxm/autumn/autumn-framework-3x/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for autumn-framework-3x

Your own site · 80×15
<a href="https://agentmods.dev/skills/henryxm/autumn/autumn-framework-3x"><img src="https://agentmods.dev/badge/skills/henryxm/autumn/autumn-framework-3x.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 620 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00620 $0.07479
Opus 5 $0.00310 $0.03740
Sonnet 5 $0.00124 $0.01496
Haiku 4.5 $0.00062 $0.00748

Measured 10d ago against content hash a7d3af5e4bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

autumn-framework-3x 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 10d 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.

Origin

This is a copy

86% identical to autumn-framework-2x — 103 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/skills/autumn-framework-3x/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autumn 3.x 框架开发（3.0.0 / 分支 3.0.0）

版本矩阵（本 Skill 唯一适用）

项 版本 / 约束
Autumn 3.0.0（cn.org.autumn:*:3.0.0，3.0.0 分支）
JDK 17+
Spring Boot 3.5.x（以根 pom.xml 为准）
MyBatis-Plus 3.x
命名空间 jakarta.*
2.x 线 禁用本 Skill：Autumn 2.0.0、JDK 8、Spring Boot 2.7 请用 autumn-framework-2x（master）

业务工程须在 AGENTS.md 或首轮对话中写明依赖的 Autumn 主版本，避免 2.x / 3.x 规范混用。

何时启用

  • 当前工作区是 autumn 仓库且检出 3.0.0 分支，或业务工程 Maven 依赖锁定 cn.org.autumn 3.0.0。
  • 提到：cn.org.autumn、ModuleService、gen、Dao、Provider、RuntimeSql、DatabaseType、statics、pages、Site、PageAware、autumn.table 等，且 栈为 JDK 17+ + Boot 3.5。

约束扫描（按需）

默认不跑：用户未提及规范体检、合并/CI 自检、constraints-scan、约束扫描等时，不要把执行 scripts/constraints-scan 当作本 Skill 的必做步骤。

何时执行：用户或任务明确要求对仓库做与 docs/AI_STANDARDS.md / docs/AI_DATABASE.md 对齐的分组体检、或声明 CI/合并门禁需要脚本结果时，再在任务根目录实际执行（勿只读文档代替执行）。

  1. 命令

    • 本仓库：工作区根执行 bash scripts/constraints-scan（或 bash scripts/constraints-scan .）。
    • 业务仓库且并列 clone 了 autumn：bash ../autumn/scripts/constraints-scan /path/to/business-root（路径按实际调整）；若无脚本则从 autumn 仓库拷贝。
    • 依赖：rg（ripgrep）；可选 AUTUMN_SCAN_SKIP_GEN=1、AUTUMN_SCAN_EXTRA=1、AUTUMN_SCAN_SKIP_REDIS=1（见脚本头注释）。

  2. 解读输出

    • 按分组 A～H 阅读（H 为 Redis TTL）；对照 docs/AI_DATABASE.md §8.5 与 docs/AI_STANDARDS.md。
    • 区分真实违规与误报（注释、测试、target/、历史生成代码等）。F 组仅为 gen 清单，不计入 TOTAL。

  3. 修复与收尾

    • 任务范围内可确定的违规：直接改代码；超出范围的在回复中写明残留风险。
    • 若本次已跑过扫描且改过相关文件，可再跑一次确认未引入新的可修复项（仍属按需，非默认）。

文档加载顺序

所有 AI_*.md 均在仓库 docs/ 下。本仓库内用 @docs/...；业务工程与 autumn 并列时用 @../autumn/docs/...（见 docs/AI_INDEX.md §4）。

  1. docs/AI_INDEX.md → 2. docs/AI_BOOT.md → 3. docs/AI_MAP.md → 4. docs/AI_STANDARDS.md（强制全文，含 §8～§14）
  2. docs/AI_DATABASE.md（多库、DatabaseType、§4.0 代码层方言标准写法、WrapperColumns、RuntimeSql、Wrapper 边界、Dao 必须 Provider）
  3. 新模块 / 代码生成 / 搭骨架：追加 docs/AI_CODEGEN.md
    按需：docs/AI_POSTGRESQL.md、docs/AI_TEMPLATES.md、docs/AI_CRYPTO.md、docs/AI_FIELD_ENCRYPT.md（实体字段存储加密、EncryptModuleService）、docs/AI_DISTRIBUTED_LOCK.md、docs/AI_ASYNC_TASK.md（TagRunnable / FinishStatus / onFinished）、docs/REDIS_RESILIENCE.md（Redis 熔断与分布式锁稳健性）、docs/REDIS_STANDALONE.md、docs/REDIS_TTL_GUIDE.md（Redis TTL / RedisExpireUtil）、docs/INSTALL_MODE_CONDITIONAL.md（安装向导 autumn.install.wizard、§0 占位默认 H2 / 可选 mysql）等。

Read the full file on GitHub · 248 lines

Changes

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.

  1. 10d ago First seen · 248 lines · 620 tokens per session scan A a7d3af5e4bad

Subscribe to this mod's changes

autumn-framework-3x is a skill published in the GitHub repository henryxm/autumn (49 stars, last pushed 15d ago), licensed Apache-2.0. It adds 620 tokens to every session and 7,479 once invoked, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to autumn-framework-2x, differing in 103 lines, and is treated as a copy.

Backend and APIsautocodinggeneratormybatistable
Related

Other skills, from other repositories

with-tanstack-query

Compose Angular Query with signal-owned Table filtering, sorting, and pagination state using reactive query options, manual row-model boundaries, direct query data, server counts, and valid injection context.

TanStack/table · 42 tokens

node-modern

Use this skill when writing, reviewing, or refactoring Node.js >= 22 TypeScript code in WrongStack. Triggers: ESM imports, fetch usage, AbortSignal, node: protocol, Web Streams, or any async patterns.

WrongStack/WrongStack · 52 tokens

api-design

Use this skill when designing, reviewing, or refactoring REST APIs in WrongStack. Triggers: user says "API", "endpoint", "REST", "request", "response", "JSON", "HTTP", "status code", "pagination", "query params", "request body".

WrongStack/WrongStack · 60 tokens

cqrs-event-sourcing

Use when designing event-driven architectures, evaluating aggregate boundaries, deciding between event sourcing and current-state storage, building read models, or when a codebase has overlapping domain objects emitting events.

mattwynne/yaks · 41 tokens

browser-spa-framework

Architecture/conventions for the Echo browser SPA: Go stdlib server :3740, Vite-built TS+JS SPA (embedded web/dist), JSON envelope, WebSocket hub, chat tool loop, shared appdata echo.json, internal/tools registry, tool-generated media transport (Phase 0/1), and the file-browser image/video/audio preview surface…

BrentFarris/echo · 91 tokens

MCP Integration Assistant

Helps design and implement Model Context Protocol (MCP) server integrations for AI agents.

Notysoty/openagentskills · 23 tokens