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 skills add MisonL/Ling --skill cybernetic-systems-engineeringgit clone --depth 1 https://github.com/MisonL/LingWrote 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/misonl/ling/cybernetic-systems-engineering)<a href="https://agentmods.dev/skills/misonl/ling/cybernetic-systems-engineering"><img src="https://agentmods.dev/badge/skills/misonl/ling/cybernetic-systems-engineering/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.
<a href="https://agentmods.dev/skills/misonl/ling/cybernetic-systems-engineering"><img src="https://agentmods.dev/badge/skills/misonl/ling/cybernetic-systems-engineering.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00139 | $0.08586 |
| Opus 5 | $0.00069 | $0.04293 |
| Sonnet 5 | $0.00028 | $0.01717 |
| Haiku 4.5 | $0.00014 | $0.00859 |
Grade A, and why
cybernetic-systems-engineering 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 6d 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.
This is a copy
100% identical to cybernetic-systems-engineering — 0 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.
How it starts
The opening of the file, as written. The whole thing — 793 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybernetic Systems Engineering（CSE）
把软件开发当作一个闭环控制系统来做：
- 被控对象（Plant）：代码库 + 运行时环境 + 依赖 + 数据 + 测试系统
- 控制器（Controller）：你（Agent）+ 你的计划、策略、节奏控制
- 传感器（Sensors）：测试、构建日志、运行日志、指标、复现脚本、审计文档
- 执行器（Actuators）：代码修改、配置变更、依赖升级、回滚、文档更新、测试补强
- 参考输入（Reference）：需求、issue、验收标准、SLO/SLA、业务边界
- 输出（Output）：实际行为（通过/失败测试、运行结果、性能数据、门禁结果）
- 误差（Error）：参考输入与输出之间的差距
- 扰动（Disturbance）：环境差异、并发、flake、脏状态、真实 schema 漂移
- 时滞（Delay）：慢测试、CI 排队、真实环境依赖、发布窗口
本 skill 的目标不是“让你会用控制论术语”，而是让你在复杂工程任务中：
- 先建立正确的观测与误差定义
- 再用最小控制输入减少误差
- 用分层验证防止振荡与假收敛
- 用总体设计视角控制复杂性
项目级控制拓扑
CSE 不只处理“当前这一条任务怎么修”，还要先回答“这个项目由谁控制、在哪一层控制、跨模块如何协调”。
从控制层级看，CSE 默认同时存在两套闭环：
- 任务级闭环
- 面向单个 issue、单次 patch、单轮验证
- 关注最小控制输入、最小 failing case、分层验证
- 项目级控制拓扑
- 面向多模块、多团队、多阶段演化
- 关注总体设计部、控制结构、跨模块协调、边界冻结与升级路径
如果只建立任务级闭环，而没有项目级控制拓扑，常见结果是：
- 单个 patch 看起来正确，但把复杂性偷偷转移到别的模块
- 局部验证通过，但共享接口、共享状态或共享基础设施被无意破坏
- 每个人都在改“自己眼前那一层”，但没有人对整体误差负责
因此在以下场景，必须先补项目级控制拓扑，再进入具体修复：
- 改动跨 2 个及以上模块、服务或语言边界
- 需要同时改代码、配置、schema、运行流程中的两类以上对象
- 任务会影响共享接口、共享状态、共享基础设施或统一门禁
项目级控制拓扑至少要回答四个问题：
- 总体设计部在哪里
- 谁负责维护项目级参考输入、关键边界和最终裁决
- 控制结构是什么
- 本次问题主要落在哪些层，哪些层只能观测，哪些层允许施加控制输入
- 跨模块协调怎么发生
- 哪些模块存在强耦合，改动会沿什么路径外溢，谁需要被显式通知或升级
- 哪些边界先冻结
- 哪些接口、schema、门禁口径在本轮不能被顺手改写
控制面 / 数据面 / 状态面
为了避免“看起来只是改一行代码，实际上改穿了整个系统”，复杂任务开始前必须先识别本次改动主要落在哪一面：
- 控制面
- 负责决定系统如何调节自己
- 典型对象：限流、重试、熔断、路由、灰度、回滚、门禁、调度策略
- 数据面
- 负责承载真实业务流量和核心处理路径
- 典型对象：请求处理、任务执行、核心计算、主链调用、用户可见结果
- 状态面
- 负责保存共享事实、恢复锚点与跨节点一致性
- 典型对象：数据库、schema、缓存、队列、事件日志、检查点、幂等键
默认要求：
- 先标出本次改动的主落点在哪一面
- 再标出会被连带影响的次级面
- 如果一次改动同时触碰两面以上，必须显式写出复杂性是如何转移的
一个典型例子：
- 把重试、限流从业务代码下沉到 mesh 或统一网关
- 不是“复杂性消失了”
- 而是复杂性从数据面转移到了控制面
- 把会话、任务进度或幂等信息从应用内存迁到 Redis / 数据库
- 不是“状态更简单了”
- 而是状态复杂性从节点内部转移到了状态面
如果主落点都判断不清，默认先不要改实现，而是先补控制结构说明。
复杂性转移账本
复杂性不会凭空消失，只会被下沉、上浮或转移到别处。
因此每次声称“系统更简单了”时，都应至少记一条复杂性转移账本：
| 字段 | 说明 |
|---|---|
| 复杂性原位置 | 复杂性原来压在哪一层、哪个模块、哪条链路 |
| 新位置 | 复杂性被转移到了哪里 |
| 收益 | 本次转移换来了什么 |
| 新成本 | 新增了什么依赖、运维成本或观测成本 |
| 失效模式 | 转移后最可能新增什么故障模式 |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 793 lines · 139 tokens per session scan A 3cd8297260c9
cybernetic-systems-engineering is a skill published in the GitHub repository MisonL/Ling (8 stars, last pushed 5mo ago), licensed MIT. It adds 139 tokens to every session and 8,586 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cybernetic-systems-engineering, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.