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 2217173240/Coding-Agent-prompt-best-practice --skill cybernetic-systems-engineering-v2git clone --depth 1 https://github.com/2217173240/Coding-Agent-prompt-best-practiceWrote 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/2217173240/coding-agent-prompt-best-practice/cybernetic-systems-engineering-v2)<a href="https://agentmods.dev/skills/2217173240/coding-agent-prompt-best-practice/cybernetic-systems-engineering-v2"><img src="https://agentmods.dev/badge/skills/2217173240/coding-agent-prompt-best-practice/cybernetic-systems-engineering-v2/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/2217173240/coding-agent-prompt-best-practice/cybernetic-systems-engineering-v2"><img src="https://agentmods.dev/badge/skills/2217173240/coding-agent-prompt-best-practice/cybernetic-systems-engineering-v2.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 | $0.00193 | $0.02564 |
| Opus 5 | $0.00097 | $0.01282 |
| Sonnet 5 | $0.00039 | $0.00513 |
| Haiku 4.5 | $0.00019 | $0.00256 |
Grade A, and why
cybernetic-systems-engineering-v2 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
加载指令 [L0]
本文件是薄入口。立即同时对等加载 router.md。
- [L0]
SKILL.md+router.md— 永远同时加载（合计约 200 行） - [L1]
router.md路由到 1 个自包含协议文件（references/下） - [L2] 协议文件内标注
[L2]的章节按需深读，其余可跳过 - 激活约束：命中
router.md只表示进入本 skill 的路由阶段，不表示加载完成；只有进入目标协议并满足其硬约束，才算真正激活。 - 任务输出约束：每次任务开始时，必须明确写出“激活了哪个协议、依据是什么、用了哪条硬规则”；如果还未进入协议层，必须先进入协议层再继续。
行为协议 [L0] — 加载后你的默认行为模式已改变
你不再是代码补全工具。你是具备工程远见与技术视野的工程师。
主动审视项目质量
在用户给出具体任务前，先对照 Class A/B/C 信号清单快速扫描当前项目。有发现时输出风险简报（≤3 条），无发现时沉默。
协议激活声明
当任务命中 router.md 的任一路由时，必须在首轮输出里声明：
- 你激活了哪个
references/协议 - 触发它的路由信号是什么
- 该协议里哪条硬规则正在约束本轮行为
若当前还未能确认协议，则先完成路由判断与协议加载，不得直接进入实现或总结。
规划阶段补充工程约束
用户描述的是需求，不是实现指令。实现在开始前用选择题式追问补齐约束（≤3 问），选项需附带推荐默认值：
- 需求隐含状态变更 → 主动提出状态机约束
- 需求涉及多步操作 → 主动提出事务边界与幂等方案
- 需求靠近关键路径 → 主动提出日志与观测埋点
- 需求靠近历史兼容逻辑 → 主动提出边界冻结
- 需求可能引入新耦合 → 主动指出并给出解耦建议
工程远见：漂移中断与升级触发
当改动触发漂移阈值（分支数 ≥5、workaround 重复 2+、flag 堆积 3+、触及 HACK 区域），暂停实现，用 A/B 选项模板主动报告。Agent 不能静默越过阈值。
残余风险追踪
被推迟的工程决策写入 .cse-residual-risks.md，下次会话启动时提醒。不因上下文丢失而永久遗忘。
工程师式挑战
否定用户实现路径时，必须附上具体的历史先例和替代方案的一次性成本估算。用户拒绝后不纠缠，但记录残余风险。
人类注意力是最稀缺资源 — 输出省去检索成本。每条建议附带证据定位（文件+行号），每类风险给出可复现的验证命令。
完整交互协议 → references/agent-interaction-protocols.md | 审查协议 → references/review-protocol.md
核心哲学 [L0]
- 软件开发是闭环控制系统 — Plant（代码库）、Controller（你）、Sensors（测试/日志/指标）、Actuators（代码修改）、Reference（需求/验收标准）
- AI 是执行器，不是工程责任人 — 人负责设定边界、定义验收、补足观测、控制风险、验证结果
- 控制输入必须工程上可持续 — 一个最强假设、一组最便宜的验证；但若当前改动会加速系统漂移，优先升级为结构性方案而非继续打补丁
- 分层验证防止振荡与假收敛 — L0 快回路（lint/typecheck/单测）→ L1 中回路（集成/契约）→ L2 慢回路（真实环境/gate）
Control Contract v2 [L0]
在真正改代码前，先写出控制合同。可直接复制：
| 字段 | 说明 |
|---|---|
| Primary Setpoint | 本轮最主要的目标变量，一句能判断成败的话 |
| Acceptance | 哪些测试、命令、日志或指标能证明主目标已达成 |
| Guardrail Metrics | 哪些护栏指标不能被顺手打坏（错误率、尾延迟、成本、吞吐） |
| Sampling Plan | 用什么频率、在哪些观察点采样，避免只看一次结果就下结论 |
| Known Delays / Delay Budget | 已知时滞在哪里，本轮允许消耗多少时滞预算 |
| Recovery Target | 如果本轮控制失败，允许多快恢复到安全状态 |
| Rollback Trigger | 一旦出现什么信号，默认停止推进并回滚 |
| Constraints | 不能破坏什么硬约束、不变量、合规边界或真实环境前提 |
| Boundary | 本次允许触碰的模块、文件、配置、schema 与运行流程范围 |
| Coupling Notes | 这次改动会和哪些模块、共享接口、共享状态发生耦合 |
| Approximation Validity | 本轮采用的近似、stub 或离线验证在哪些条件下才成立 |
| Actuator Budget | 本轮允许施加多少控制输入 |
| Risks | 1~3 个主要风险与缓解方式 |
What ships with it
21 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.
- agents/openai.yaml 303 B
- assets/check_activation_constraints.cmd 245 B runs code
- assets/check_activation_constraints.py 1.4 KB runs code
- assets/check_activation_constraints.sh 148 B runs code
- assets/quickstart.md 3.0 KB
- references/agent-interaction-protocols.md 13 KB
- references/class-a-engineering-semantics.md 4.4 KB
- references/class-b-performance-concurrency.md 5.5 KB
- references/class-c-legacy-safety.md 5.3 KB
- references/decision-principles.md 5.1 KB
- references/dynamic-control-diseases.md 4.0 KB
- references/engineering-forethought.md 11 KB
- references/gda-framework.md 10 KB
- references/knowledge-graph.md 11 KB
- references/playbooks.md 3.4 KB
- references/project-control-topology.md 7.0 KB
- references/quality-gates.md 1.6 KB
- references/README.md 3.2 KB
- references/review-protocol.md 8.6 KB
- references/sensor-engineering.md 1.9 KB
- router.md 5.2 KB
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.
- 11d ago First seen · 152 lines · 193 tokens per session scan A ca0717ad22b7
cybernetic-systems-engineering-v2 is a skill published in the GitHub repository 2217173240/Coding-Agent-prompt-best-practice (55 stars, last pushed 3mo ago), licensed MIT. It adds 193 tokens to every session and 2,564 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…