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-guidegit 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-guide)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/code-to-guide"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/code-to-guide/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-guide"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/code-to-guide.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 | $0.00133 | $0.03080 |
| Opus 5.5 | $0.00053 | $0.01232 |
| Sonnet 5.5 | $0.00027 | $0.00616 |
| Haiku 4.5 | $0.00013 | $0.00308 |
Grade A, and why
code-to-guide 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
§0 角色定位与边界
做什么：读一个已有项目的代码，理解它的模块结构、数据模型、接口设计和业务逻辑，产出一套 AI 友好的项目导览文档（docs/<项目名>/）。
不做什么：不改项目代码；不建七层文档体系；不产出需求文档（L1）；不跟随项目生命周期演进。
与其他 skill 的区别：
docs-from-code：从代码反推 L1 需求，用于七层体系。本 skill 产出的是"项目说明书"，不是需求。code-to-7layer：七层冷启动，重型架构治理。本 skill 产出物极其轻量，只是导览。doc-layer-system：七层文档治理规范本体。本 skill 与之完全无关。
§1 何时触发
触发：
- 接手陌生或遗留代码库，需要快速建立整体认知
- 向团队其他成员（或 AI）介绍一个项目
- 需要"让 AI 读一遍就能理解这个项目"的结构化文档
不触发：
- 要建七层文档体系 → 用
code-to-7layer - 要补 L1 需求文档 → 用
docs-from-code - 要修改/扩展项目代码 → 不适用本 skill
§2 五阶段工作流总览
Phase 1: 项目扫描
└─ 主 agent 亲自做：find/ls 摸结构 → 产出模块地图
Phase 2: 模块拆分 + Agent Team 并行派发
└─ 按内聚模块拆任务 → 并行 Explore+sonnet 子 agent（≤6~8 个）
Phase 3: 汇总两层文档
├─ 参考层（是什么）：按模块并行整理，字段表/接口表/枚举
└─ 理解层（为什么/怎么用）：跨模块综合或专门追踪业务流程
Phase 4: 建 README 索引 + 阅读路径
└─ README = AI 唯一入口，含文档地图、推荐阅读路径、术语速查
Phase 5: 新鲜视角自检
└─ 单独 agent 只读文档（禁读代码），复述项目 → 列出看不懂的点
§3 Phase 1 — 项目扫描
主 agent 亲自执行，不派发子 agent。
扫描步骤
- 读项目根目录（
ls、find . -maxdepth 3 -type f -name "*.java|*.go|*.ts|*.py" | head -50） - 读 README/AGENTS.md（若有）
- 统计文件规模：
find . -name "*.java" | wc -l（按语言调整后缀） - 识别模块边界：Maven 多模块 → 看 pom.xml；Go → 看目录名；JS/TS → 看 package.json/目录结构
产出：模块地图
一份 Markdown 表格，包含：
| 模块名 | 目录路径 | 核心职责（一句话） | 代表文件（2~3 个） |
|---|
模块地图用途：
- 指导 Phase 2 的 agent 派发（每行 = 一个 agent 任务）
- 成为 Phase 4 README 文档地图的基础
语言约定
优先读项目 AGENTS.md，默认跟随用户对话语言（通常中文）。
§4 Phase 2 — 模块拆分 + Agent Team 派发
拆分原则
- 按内聚领域/模块拆，不按文件数
- 每个 agent 一个 bounded context（一个模块的全部层：entity/service/api/dto）
- 模块过大（>60 个文件）则按子领域再拆
- 模块过小（<5 个文件）则与相邻模块合并
- 数量上限：6~8 个 agent，防主 agent 调度过载与上下文爆炸
子 agent 规约
每个子 agent 必须：
subagent_type: Explore（只读，不写文件）model: sonnet- prompt 里给明确文件清单（路径列表，不是"自己去找"）
- 要求返回结构化中文报告，包含：
- 实体/POJO 字段表（字段名、类型、说明）
- 核心接口/方法清单
- 关键枚举值
- 模块间依赖关系（调用了哪些其他模块的什么接口）
- 一句话模块职责总结
- 声明"只调研，不写任何文件"
并行派发
单条消息中包含所有 Agent 工具调用，使它们并行运行。
模板 prompt（子 agent）
你是一个只读代码调研 agent。任务：调研 <模块名> 模块，整理结构化中文报告。
目标文件清单（只读这些，不要扩展搜索）：
- <文件路径1>
- <文件路径2>
...
请报告：
1. 实体/POJO 字段表（字段名 | 类型 | 说明）
2. 核心接口/服务方法清单（方法签名 + 一句话说明）
3. 关键枚举值（枚举名 + 各值含义）
4. 跨模块依赖（调用了哪些模块的哪些接口）
5. 一句话模块职责总结
不要写文件，只返回报告文本。
What ships with it
4 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.
- 29d ago Changed a25b3dee8c28
- 1mo ago First seen · 269 lines · 133 tokens per session scan A 3fe2a2196eb2
code-to-guide is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 133 tokens to every session and 3,080 once invoked, about $0.0005 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…