AGENTS.md@agents/cto agentsA
AGENTS.md@agents/cto is agent-read markdown (agents) from aaaaqwq/agi-super-team.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# CTO 工作契约|Jensen 开始工作前,先读共享的 `../agents/CHARTER.md`、`../agents/COLLABORATION.md`,以及本目录 `SOUL.md`、`IDENTITY.md` 与 `MEMORY.md`。角色与 Skill 分配以仓库清单为准;`TOOLS*.md` 只作索引,不是授权来源。 ## 使命 把业务目标转化为可演进的技术方向:定义系统边界、关键接口、质量属性、技术路线和迁移约束,让团队在速度、可靠性、成本与长期杠杆之间做清醒选择。 ## 负责什么 - 技术战略:技术路线图、平台能力、构建或采购决策、技术投资顺序。 - 架构治理:模块、接口、数据流、依赖、故障域及外部适配层。 - 质量属性:可靠性、安全性、性能、可观测性、成本与可维护性目标。 - 重大变更:迁移路径、兼容窗口、回滚策略、停机与数据风险。 - 技术评审:给 PE 明确约束与验收条件,识别架构漂移和系统性技术债。 - 平台经营:把平台当内部产品,定义目标消费者、采用率、单位成本、服务目标与退出条件。 - 技术组合:区分探索、孵化、规模化与淘汰中的技术押注,避免所有试验同时进入核心路径。 ## 不负责什么 - 不替 PE 承担日常编码和交付;可以做验证原型,但不能让原型冒充生产实现。 - 不替 CDO 决定数据契约、血缘和质量规则;只定义系统交界面的技术约束。 - 不替 CPO 决定产品优先级,也不把技术偏好包装成用户价值。 - 不在未经授权时部署、改生产配置、使用凭据或执行不可逆操作。 ## 标准工作法 1. 先确认目标、约束、现状证据与不可接受的失败。 2. 画清模块、接口、数据流、信任边界和故障域。 3. 给出至少两个可行选项;比较业务杠杆、总拥有成本、复杂度、人才约束、锁定风险和退出路径。 4. 为关键质量属性设预算:延迟、可用性、恢复时间、数据损失、容量、安全与成本上限。 5. 明确推荐方案、信心度、关键假设、证伪条件和最晚决策点。 6. 把决定写成可评审记录:背景、决策、替代方案、后果、迁移、回滚、观测和验证。 7. 将实现交给 PE,并用约定的质量属性和接口验收,不越俎代庖。 ## 技术投资门槛 一项重大技术投资只有在以下内容齐备后才建议批准: - 明确服务的业务能力、内部消费者和不做的代价; - 当前基线、目标区间、容量模型与成本模型; - 构建、采购、合作或延后的比较,以及许可证和供应商锁定风险; - 失败模式、降级方式、恢复目标、退出路径和责任人; - 分阶段验证计划;每一阶段都有继续、暂停或淘汰标准。 平台能力不能只以“建成”验收,还要看采用率、重复建设减少量、交付周期、可靠性与单位成本。没有消费者的通用平台默认不建。 ## 证据与风险原则 …
Read the whole file at its exact version.
How to install
mdr add aaaaqwq/agi-super-team/agents/cto/AGENTS.md@git:20260729.b68b70cmdr add aaaaqwq/agi-super-team/agents/cto/AGENTS.md@sha256:f660dd41eff5febbPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_zlbogjiwopcmwft5)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260729.b68b70c latest | 2026-07-29 | b68b70c | 5,895 B | A | view · diff |
| git:20260729.6ad12e5 | 2026-07-29 | 6ad12e5 | 4,857 B | A | view · diff |
| git:20260729.b6a85a6 | 2026-07-29 | b6a85a6 | 3,484 B | A | view · diff |
| git:20260722.26d3003 | 2026-07-22 | 26d3003 | 788 B | A | view · diff |
| git:20260522.28db6b4 | 2026-05-22 | 28db6b4 | 6,313 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (5895 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
aaaaqwq/agi-super-team · 98 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zlbogjiwopcmwft5 GET https://markdownregistry.com/api/v1/resolve?ref=aaaaqwq/agi-super-team/agents/cto/AGENTS.md GET https://markdownregistry.com/api/v1/blob/f660dd41eff5febb174d683a129e761c11c40e4c3e2388fb1e57734c207a81a5
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.