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 construction-blueprintgit 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/construction-blueprint)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/construction-blueprint"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/construction-blueprint.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.02218 |
| Opus 5 | $0.00046 | $0.01109 |
| Sonnet 5 | $0.00019 | $0.00444 |
| Haiku 4.5 | $0.00009 | $0.00222 |
Grade A, and why
construction-blueprint 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 8d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
施工蓝图
本 skill 是任务级详细设计的施工层,用户级通用,可跨项目使用。
它解决的问题:直接从设计跳到代码,评审只能发生在代码写完之后——错误已扩散进几十个文件,大 diff 评审有疲劳和沉没成本,范围蔓延和漏改反而最难看出来。施工蓝图把评审前移:
作用 = 代码镜像 + 施工指南:开工前把"动哪些文件、按什么顺序、关键处长什么样"钉死,让对抗评审打在图纸上。蓝图评审拦"方向错",代码后检查拦"手抖错",两道闸缺一不可。
与轻量设计方案(lightweight-design skill)的海拔分工:
轻量设计方案 ── 决策海拔 ── 人看的,用户审核拍板
↓
施工蓝图 ────── 代码海拔 ── AI 看的,开工前对抗评审(本 skill)
↓
施工 → 回补七层文档
关键性质:一次性消耗品。 L5/L6 禁止代码镜像是因为它们是长期真值、代码一改就腐烂;蓝图施工完即归档,来不及腐烂,所以文件清单、方法签名、伪代码在本层全部合法。
1. 输入与何时用
输入(按优先级):
- 轻量设计方案(首选——已拍板的决策是蓝图的裁判标准)
- 七层正式文档(任务直接基于现存设计施工时)
- 需求 + 用户当轮聊天确认(必须在蓝图里显式登记为"真值来源")
用:中大任务施工前必经;凡是写了轻量设计方案的任务,默认接一份蓝图。
可跳过:
- 小改动(计划模式足够)
- 纯文档任务
- 轻量设计方案本身已足够简单、变更面只有一两个文件时(此时计划模式即蓝图)
2. 粒度铁律(防"代码写两遍"反模式)
蓝图写得太细 = 把代码写两遍,又慢又没增益。粒度卡死在:
| 内容 | 粒度 |
|---|---|
| 变更清单(主体) | 文件级:一文件一行,新增/修改/删除 + 一句"改成什么样" |
| 关键实现点 | 仅歧义点/风险点下沉到逻辑级(允许方法签名、伪代码) |
| 纯透传 / CRUD / 标准操作 | 只列文件,不展开 |
判定句:蓝图字数接近预估代码量 → 写过头了,砍。
3. 文档模板
# 施工蓝图:{任务名}
> 上游输入:{轻量设计方案路径 / 七层文档 / 用户决策}
> 状态:待评审 / 已评审通过 / 施工中 / 已归档
## 1. 任务边界
改什么 + 明确不改什么(负面清单,限制范围的主力)
## 2. 变更清单 ★代码镜像主体
逐文件三分类(含 DB migration、配置、脚本):
### 新增
- `path/to/NewFile`:一句意图
### 修改
- `path/to/File`:改哪部分、改成什么样(一句)
### 删除
- `path/to/OldFile`:为什么退出
## 3. 关键实现点(仅少数点,逻辑级)
对有歧义/有风险的点写到逻辑级;允许签名与伪代码
## 4. 施工切片
| 切片 | 内容 | 前置 | 完成判定 |
每片独立可编译/可验证;判定写得可执行,不写"完成即完成"
## 5. 历史资产退出(重构/替换类任务必写)
旧表 / 旧代码 / 旧格式 / 旧接口语义:删什么、何时删、是否留兼容层
## 6. 红线自检
项目分层方向 / 域边界 / 工程红线 逐条打勾(清单由项目补丁注入)
## 7. 验收映射 ★对抗评审主靶面
| 轻量设计决策点 | 落在哪条变更条目 |
有决策无落点 = 漏;有落点无决策 = 越权加戏
## 8. 验证与回归
编译 / 测试 / 接口脚本是否同步 / 是否需手工验证(逐项判断,不留空白)
## 9. 风险与回滚
最坏情况怎么退(一段话)
## 10. 可开工性结论
只许三种:可以 / 基本可以但差非阻塞补充 / 不可以+阻塞清单
4. 对抗评审协议(开工前的那道闸)
评审输入:蓝图 + 轻量设计方案 + 相关契约文档(接口/数据库层)。
三个靶面(恰好是代码评审最容易漏的):
| 靶面 | 评审问题 |
|---|---|
| 范围越界 | 变更清单里有没有不在任务边界内的文件?有没有动了不该动的域/模块? |
| 遗漏 | 该改的调用点列全了吗?接口改了,所有消费方都在清单里吗? |
| 方案性错误 | 关键实现点与已拍板决策一致吗?分层/事务边界/批量查询等是否违反项目规范? |
裁判标准:第 7 节验收映射表逐条核对——评审不是泛泛"看看方案好不好",而是拿轻量设计当裁判逐条对。
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.
- 8d ago First seen · 175 lines · 93 tokens per session scan A b378f35c2245
construction-blueprint is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 14d ago), licensed Apache-2.0. It adds 93 tokens to every session and 2,218 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
repo-conventions
NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
dev-research
A research workflow that uses NotebookLM, a tool for asking questions about a selected collection of documents, to answer development questions with citations.
budget-continue
Show 4-option continuation prompt when session budget is low. Options: remind later (CronCreate), auto-continue locally (Desktop task), auto-continue in cloud (Cloud task), continue now. Trigger when: budget warning fires, session limit reached, context is full, user sees budget warning.