AI+Human软件交付方法论，具备风险分级治理、可执行门、循证生命周期及工具无关的代理集成。麻省理工学院。
概览
最新发布：v7.1.2-alpha ·主线：未发布 ·发布状态：ALPHA ： 7.0.0（实时文档验证的框架版本，由脚本/check-version-declared.sh 读取） |： MIT ：活跃 ：@dttai71 ：首次阅读者和团队决定是否采用该框架：2026-12-26 谁会阅读此文：任何决定采用该框架，还是首次打开此仓库的人。时间：首先。需要十分钟;布局和阅读顺序在本页末尾。 版本7是框架的第二代：重建，而非升级。第一代（v6及更早版本）存档时未修改，存档于archive/;仍保留的内容被收割到这棵树中，每个源代码一行，MIGRATION-MAP.md。除非第一代有行，否则不适用。 1. 一种用AI代理和少数人——通常只有一人——构建软件的方法论。2. 你拥有四个资产。其余的由供应商提供：代理、模型、运行时、会话中编排。3.
概述（AI 翻译）
最新发布：v7.1.2-alpha ·主线：未发布 ·发布状态：ALPHA
版本：7.0.0（实时文档验证的框架版本，由scripts/check-version-declared.sh读取）|许可：MIT
状态：活跃 所有者：@dttai71 消费者：首次阅读者和团队决定是否采用该框架 审核人：2026-12-26
谁会阅读此文：是否采用该框架，或首次打开该仓库的人。 何时：首先。只需十分钟;排版和阅读顺序在本页末尾。
框架是什么
版本7是框架的第二代：重建而非升级。第一代（v6及更早版本）存档于archive/，未修改;仍存的部分被收割到这棵树中，每个源一行出现在MIGRATION-MAP.md。除非第一代有行，否则不适用。
- 一种用AI代理和少数人——通常是一个人——构建软件的方法论。
- 你拥有四个资产。供应商提供其余：代理、模型、运行时、会话中编排。
- 规则分为三类。只有确定性检验会被阻挡。
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
SDLC Enterprise Framework
Latest release: v7.1.2-alpha · Main: Unreleased · Release status: ALPHA
Version: 7.0.0 (the framework version live docs are verified against, read by scripts/check-version-declared.sh) | License: MIT
Status: ACTIVE Owner: @dttai71 Consumer: first-time readers and teams deciding whether to adopt the framework Review by: 2026-12-26
Who reads this: anyone deciding whether to adopt the framework, or opening this repo for the first time. When: before anything else. It takes ten minutes; the layout and reading order are at the end of this page.
What the framework is
Version 7 is the framework’s second generation: rebuilt, not upgraded. The first generation (v6 and earlier) is archived unmodified in archive/; what still holds was harvested into this tree, one row per source in MIGRATION-MAP.md. Nothing from the first generation applies unless it has a row there.
- A methodology for building software with AI agents and a few people — often one.
- You own four assets. Vendors supply the rest: agents, models, runtimes, in-session orchestration.
- Rules sit in three classes. Only deterministic checks block.
- Controls scale with the risk of the thing being built, not with team size.
- A rule names a runnable command and the real incident (burn case) that justifies it.
- A rule without a command is reference material, not a rule.
- Gates default to ADVISORY with a counter and a deadline, and climb only on measured rates. A narrow control against irreversible harm may enter MACHINE directly — only under the exception contract in
controls/rule-contract.md. - Incidents flow back into rules through one path (
lessons-to-rules). - The framework gates itself in CI: doc count, rule tables, version declarations.
- Promise: fewer rules, more of them enforced. Every section says what it shortens.
The four assets you own
| Asset | What it is | Where it lives |
|---|---|---|
| Policy | tiers, rules, hats (role files), approvers | one policy repo (adoption) |
| Repo knowledge | domain context an agent needs: AGENTS.md, pointers to sources |
each product repo |
| Runnable gates | scripts with exit codes 0/1/2 and a --selftest |
scripts/ here; the policy repo |
| Eval set | fixed cases with a published taxonomy, to compare agents and configs | the policy repo |
Everything else is rented: agent CLIs, subagents, skills, hooks, models, CI runners.
Adapters to them are generated and disposable. The policy is not. This repo’s skills/ are such adapters: they route an agent to the files that hold the rules, and are not a fifth asset.
Shortens: you build and maintain nothing a vendor already ships.
Tier by risk of the artefact, not headcount
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add minh-tam-solution/sdlc-enterprise-framework