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 BackToCimaCoppi/Praxis --skill code-to-7layergit clone --depth 1 https://github.com/BackToCimaCoppi/PraxisWrote 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/backtocimacoppi/praxis/code-to-7layer)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/code-to-7layer"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/code-to-7layer/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/backtocimacoppi/praxis/code-to-7layer"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/code-to-7layer.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 | $0.00157 | $0.08758 |
| Opus 5.5 | $0.00063 | $0.03503 |
| Sonnet 5.5 | $0.00031 | $0.01752 |
| Haiku 4.5 | $0.00016 | $0.00876 |
Grade A, and why
code-to-7layer 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 29d 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 — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.
从代码冷启动生成七层文档反推总控
交付物边界（必读）：本 skill 的交付物是 Phase 0–2（扫描 + 骨架确认 + 任务总控文档创建）。具体层的文档撰写属于 Phase 3，通过
$control逐子任务推进。本 skill 是编排器，不是文档生成器。代码、实时数据库和运行行为只能形成候选规格与冲突证据；正式 L1~L7 必须经层内裁决与当前态重写后才能冻结。
不适用场景：
- 代码与现有文档的增量同步 → 用
doc-layer-systemskill - 仅补写 L1 需求层 → 用
docs-from-codeskill
依赖 skill（子任务执行时按需引用，不需要预加载）：
doc-layer-system§0.2（项目形态与层裁剪）— 决定哪些层适用doc-layer-system§0.3（业务域与功能模块）— 域/模块等价性约定docs-from-code（L1 反推方法论）— L1 层子任务执行时引用control（总控文档格式与推进机制）— Phase 2 生成总控文档时引用
§1 冷启动流程总览
Phase 0 Phase 0.5 Phase 1 Phase 2 Phase 3（总控驱动）
扫描代码 → 活跃面识别 → 一次性骨架确认 → 生成总控文档 → 逐层逐域逐子任务产出文档
↑ 本 skill 止步于此
Phase 3 的执行：通过 $control <关键词> Tn 按子任务推进，每个子任务的提取指南见 §5。
§2 Phase 0：自动扫描项目结构
进入 skill 后，无需用户输入，直接扫描：
2.1 项目形态检测（三层检测）
第一层：仓库级（是否为 monorepo/多子仓）
| 信号 | 判断 |
|---|---|
pnpm-workspace.yaml / lerna.json / nx.json / rush.json |
monorepo，进入子项目级检测 |
packages/ / apps/ / services/ 下存在多个独立子目录（各自有构建文件） |
多子仓，每个子目录独立判断 |
| 无上述信号 | 单仓，直接进入子项目级检测 |
第二层：子项目级（每个子仓/单仓判断框架）
| 信号文件 | 框架/语言 | 初步形态 |
|---|---|---|
pom.xml / build.gradle |
Java/Kotlin 后端 | 纯后端候选 |
requirements.txt / pyproject.toml |
Python 后端 | 纯后端候选 |
go.mod |
Go 后端 | 纯后端候选 |
package.json 含 express/koa/fastify/nestjs |
Node 后端 | 纯后端候选 |
package.json 含 react/vue/angular/next/nuxt |
前端框架 | 前端候选 |
.wxml 文件 / wx: 标签 |
微信小程序 | 前端候选 |
| 同一构建单元同时含后端框架 + 前端框架 | 全栈 | 全栈候选 |
第三层：运行时入口级（确认实际执行形态）
| 信号 | 判断修正 |
|---|---|
main() / Application.run() / app.listen() |
确认后端服务形态 |
handler / serverless.yml / template.yaml（SAM） |
serverless 函数形态，输出接口契约但无长驻服务 |
Dockerfile CMD / entrypoint.sh |
确认容器化形态 |
无 fetch/axios/xhr 调用（前端项目） |
确认离线前端形态 |
异步入口检测（同步进行，不单独成层）：
| 信号 | 类型 |
|---|---|
@Scheduled / @Cron / cron 表达式 |
定时任务 |
@KafkaListener / @RabbitListener / @SqsListener |
消息队列消费者 |
@EventListener / ApplicationEvent / EventEmitter |
内部事件 |
WebSocket handler / @SubscribeMessage |
WebSocket |
/webhook 路由 / callback 路由 |
外部 Webhook 入站 |
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.
- 29d ago Changed 88ec6c534d21
- 1mo ago First seen · 552 lines · 157 tokens per session scan A 35096b9e380c
code-to-7layer is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 157 tokens to every session and 8,758 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
browser-tools
Safety rules over the upstream agent-browser skill (scraping ethics, auth, request pacing, local URLs). URL policy is the Claude Code sandbox's job when the operator enables it. Use for browser automation.
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
architecture-patterns
Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…