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 doc-layer-systemgit 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/doc-layer-system)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/doc-layer-system"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/doc-layer-system/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/doc-layer-system"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/doc-layer-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00185 | $0.22089 |
| Opus 5.5 | $0.00074 | $0.08836 |
| Sonnet 5.5 | $0.00037 | $0.04418 |
| Haiku 4.5 | $0.00018 | $0.02209 |
Grade A, and why
doc-layer-system 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 — 962 lines — stays where its author put it; the contents beside it link to each section on GitHub.
七层文档体系
本 skill 是七层文档体系的可执行版本，用户级通用，可跨项目使用。
项目特定约定（目录路径、域列表、死亡线区域清单、金标准领域清单等）通过项目级 skill 补丁扩展，不写进本文件。
0. 适用范围与形态映射
本 skill 的七层划分是功能性抽象，可跨技术形态使用。
| 抽象层 | 通用含义 | 常见实现形态 |
|---|---|---|
| L1 需求层 | 产品意图与业务规则的完整载体 | 功能文档、业务需求书、线框/原型图 |
| L2 交互规格层 | 用户可见的交互规格（可选层：无 UI 项目可省略） | Web/移动端页面视觉规格；CLI 的命令行交互规格；低保真交互流程图；状态页（loading/empty/error/disabled） |
| L3 契约层 | 系统对外暴露的接口契约 | HTTP REST API；RPC/gRPC；CLI 命令签名；事件 Schema；消息队列消息格式 |
| L4 持久化规格层 | 数据存储结构规格 | 关系型数据库表结构；KV Store Schema；文件格式规范；消息存储结构 |
| L5 客户端实现规约（可选层：无客户端项目可省略） | 客户端/前端的架构规范与主要链路 | Web/移动端前端；桌面端；CLI 客户端逻辑层 |
| L6 服务端实现规约 | 服务端/后端的架构规范与主要链路 | REST 后端；微服务；数据管道；定时任务系统；事件消费者 |
| L7 测试用例层 | 对 L1~L6 各层设计意图的验证规格 | 自动化测试用例规格；手工验证场景规格 |
L2 与 L5 是可选层：纯后端服务、CLI 工具、数据管道、事件驱动系统等项目，可在项目级补丁中声明省略 L2 和/或 L5，直接从 L1 接入 L3/L4/L6/L7。
0.1 审核能力矩阵
每层文档的每次正式变更，需要由具备对应审核能力的人确认。能力要求是通用约束，具体绑定到哪个角色/岗位/人，由项目级补丁声明；若项目缺失某项能力，也应在补丁中显式声明降级方案（例如「L4 副审由主审兼任」）。
| 层 | 主审所需能力 | 副审所需能力 |
|---|---|---|
| L1 需求 | 业务判断能力（能确认功能边界与业务规则） | 技术可行性判断能力 |
| L2 交互规格层 | 视觉与交互判断能力 | 客户端实现判断能力 |
| L3 契约层 | 契约设计能力（客户端 + 服务端双侧） | 测试设计能力 |
| L4 持久化规格层 | 存储设计能力 | 架构判断能力 |
| L5 客户端实现规约（架构治理类） | 架构判断能力 | 全体技术可参与 |
| L5 客户端实现规约（实现方案类） | 客户端实现判断能力 | 业务判断能力（涉及业务时） |
| L6 服务端实现规约（架构治理类） | 架构判断能力 | 全体技术可参与 |
| L6 服务端实现规约（实现方案类） | 服务端实现判断能力 | 业务判断能力（涉及业务时） |
| L7 测试用例 | 测试设计能力 | 业务判断能力（金标准） |
0.2 项目形态与层裁剪
不同项目形态适用不同的层组合。项目级补丁应在文件开篇声明当前形态（如 > 项目形态：纯后端）。
| 项目形态 | 适用层 | 省略层 |
|---|---|---|
| 全栈（前端 + 后端） | L1 / L2 / L3 / L4 / L5 / L6 / L7 | 无 |
| 纯后端（无独立客户端） | L1 / L3 / L4 / L6 / L7 | L2（无 UI）/ L5（无客户端） |
| 纯前端（对接外部 API） | L1 / L2 / L3 / L5 / L7 | L4（无自有持久化）/ L6（无自有服务端） |
| 纯前端（离线 / 无后端） | L1 / L2 / L5 / L7 | L3 / L4 / L6 |
说明：
- 「纯前端对接外部 API」场景中 L3 仍然适用，用于记录前端所依赖的外部 API 契约（只读，非自有）
- 裁剪后不适用的层在本项目中跳过，对应文档路径和扫描矩阵条目无效
- 项目补丁声明形态后，
code-to-7layer反推 skill 会据此自动裁剪子任务列表
0.3 业务域与功能模块
本 skill 使用**「域/模块」**作为贯穿各层的组织轴：
- 有明确领域边界的项目（DDD 实践、微服务等）：以业务域（如「用户」「订单」「支付」）为轴
- 无明确领域边界的项目（按技术模块或功能分组）：以功能模块（如「认证」「消息推送」「管理后台」）为轴
What ships with it
1 file 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.
- 29d ago Changed 9803b1a62c68
- 1mo ago First seen · 962 lines · 185 tokens per session scan A 3e02b644de34
doc-layer-system is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 185 tokens to every session and 22,089 once invoked, about $0.0007 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…