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 lightweight-designgit 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/lightweight-design)<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/lightweight-design"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/lightweight-design/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/lightweight-design"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/lightweight-design.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 | $0.00131 | $0.11938 |
| Opus 5.5 | $0.00052 | $0.04775 |
| Sonnet 5.5 | $0.00026 | $0.02388 |
| Haiku 4.5 | $0.00013 | $0.01194 |
Grade A, and why
lightweight-design 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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
轻量设计方案
本 skill 是一次任务里高风险大决策的「清算层」，用户级通用，可跨项目使用。
它解决的问题：大量任务是局部修改/改造，不值得每次重写整域 L5/L6；但只拿需求直接开工，AI 会在最危险的几个取舍上"看似合理地选错"。轻量设计就是补在中间的那一层——把会出事故的决策，在动工前、在人能拍板的地方，逐个清算到唯一选择。
与下游的分界线是【风险】，不是【海拔】。 做错会出事故（拆不动 / 牵一发动全身 / 漏钱 / 白送权益 / 越权 / 丢数据）→ 本层清算钉死； 做错只是返工（参数名 / 方法互调 / 字段内部实现）→ 不进任何文档，代码自由范围。
轻量设计方案 ── 高风险决策清算 + 影响面勘察 + 验收映射 ── 人工拍板闸（本 skill）
↓ 清算结论冻结为只读输入
测试用例设计 ── 完整用例直接写正式 L7 + 断言编号（待统一冻结）
↓
真值收敛与规格冻结 ── SD → 正式规格 → AC 对账全绿，七层一次冻完
↓
goal 章程 ───── 把裁决转成执行契约（目标+验证器+边界+切片） ── 接受红队评审（goal-charter）
↓
goal 执行 ───── 自主生产精确候选：代码 → 提交 → 测试 → 执行证据清单 → CANDIDATE_READY
↓ 候选 commit/tree + 真值基线 + 证据
候选终审 ──── 独立验收真实断言、边界形状与实现语义；闭环整改后才允许任务完成
本流程不再产出施工蓝图（它自己跟自己打架：同一份近千行文件前后给出相反的施工指令；旧技能已退役，存量文件只读）。它的两个器官各有新家：影响面勘察 + 验收映射 → 本层 §7；施工切片 → goal 章程的里程碑。 而它的第三部分「逐文件施工指令书」没有新家，是被删掉的——那是全链条唯一无上游、只能靠猜的内容，必然腐烂。
⚠️ 这一层防的是"空心设计"——决策表填满了、却把最危险的取舍一句话糊过或下放给没人细看的下游。 防空心不靠更厚的模板（模板越厚越容易被"逐项 N/A 扫一遍"形式合规糊过），靠两件事： ① 事实基线（每个高风险决策必须锚定"我在真实代码/业务真值里读到了什么"，而非"列了哪些文件"）； ② 失败标准（自检每一项都有明确的"什么算不合格"，写几个字不算过）。
0. 触发、分档与两层边界
0.1 什么时候用 / 不用
用（满足任一即考虑）：局部功能开发 / 局部重构 / 单链路改造，且存在会出事故的决策点；或任务跨多文件易范围蔓延；或用户要求"先出设计再动手"。
不用：
| 场景 | 改用 |
|---|---|
| 小改动（修 bug、加字段、单文件小改，无事故级决策） | 计划模式，零文档成本 |
| 小任务（有决策点或测试义务，单会话可完成，未命中反向升级项） | plan-goal：一份全包计划 → 业务决策负责人批准 → goal 执行 |
| 整域级设计 / 新域立项 | 直接写七层正式文档 |
| 纯执行、无决策点的机械任务 | 直接做 |
| 跨会话、多 agent 超大任务 | task-control-doc 总控（标准模式七阶段，本层是其第 ③ 阶段） |
反向升级（轻量设计也不够用，必须升正式七层 / 专项）：资金/权益/权限整链路重构 · 跨多业务域 · 不可逆数据迁移 · 阻塞级决策相互耦合、无法在一次拍板内独立收敛。别把这类硬塞进"轻量"假装轻量。
拆分前置闸（拆分必须早于评审，不许"先合评、评到一半再拆"）：起草时若发现一份方案实为不同风险档的可分离子设计（典型：一半是跨域 / 升正式 L6 的架构地基、一半是域内可一次收敛的轻量改造），必须在进对抗评审闸之前先拆开，各子设计按自己的档位（轻量 / 正式七层）独立走流程。
为什么前置：合起来评审 N 轮后才拆，母稿那 N 轮评审随即作废，拆出的每一半都要从头重评——评审轮次直接翻倍。拆分判定属本层职责，不是评审能帮你做的事。可分离判据：两部分能各自独立拍板、各自冻结、互相只以"接口 / 引用结论"耦合而非"同一决策反复横跳"。
死亡线区域的局部改造不升出本层——仍走轻量设计，但强制升评审强度（判阻塞级 + 过双闸，不得单评审放行）；只有整链路重构 / 跨多域 / 不可逆迁移才升正式七层。（区分依据 = 范围 + 不可逆程度，与项目补丁的死亡线流程对齐。）
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 20c49ba076df
- 1mo ago First seen · 428 lines · 131 tokens per session scan A 3f7e0451204f
lightweight-design is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 11,938 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
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
multi-surface-render
Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…
ai-ui-generation
AI-assisted UI generation patterns for json-render, v0.app, Google Stitch, Bolt Cloud, and Cursor workflows. Covers prompt engineering for component and full-stack app generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality…
design-system-tokens
Design token management with the W3C Design Token spec, three-tier hierarchy (global/alias/component), OKLCH color, Style Dictionary transforms, and dark mode theming. Use when creating token files, implementing theme systems, or building design-to-code pipelines.