What is design-brain?

A planning and system-design guide for software work. It can produce a short implementation plan or, for complex decisions, a detailed design covering components, data flow, technology choices, risks, and testing.

Use it to analyse requirements, choose technologies, design software architecture, identify dependencies, assess risks, and plan implementation.

It helps turn an unclear request into ordered, checkable steps and makes important design decisions and trade-offs explicit before coding begins.

How sumulige/sumulige-claude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sumulige/sumulige-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sumulige/sumulige-claude/main/.claude/skills/design-brain/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/sumulige/sumulige-claude

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sumulige/sumulige-claude/design-brain/github.svg)](https://agentmods.dev/skills/sumulige/sumulige-claude/design-brain)

Your own site

<a href="https://agentmods.dev/skills/sumulige/sumulige-claude/design-brain"><img src="https://agentmods.dev/badge/skills/sumulige/sumulige-claude/design-brain/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sumulige/sumulige-claude/design-brain"><img src="https://agentmods.dev/badge/skills/sumulige/sumulige-claude/design-brain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 929 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00929
Opus 5	$0.00000	$0.00464
Sonnet 5	$0.00000	$0.00186
Haiku 4.5	$0.00000	$0.00093

Measured 9d ago against content hash b32ec4350577, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-brain 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 9d 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.

.claude/skills/design-brain/SKILL.md · 191 lines

What it actually says

Design Brain

设计大脑 - 合并: planner + architect-design

核心职责

统一处理设计和规划工作：

需求分析 - 理解和澄清需求
架构设计 - 系统设计、技术选型
实现规划 - 步骤分解、风险评估

工作模式

模式 1：快速规划（默认）

触发：一般任务
输出：简洁的实现步骤
耗时：< 2 分钟

模式 2：深度设计

触发：--deep 或复杂架构决策
输出：完整设计文档
耗时：5-10 分钟

快速规划流程

1. 理解需求（30s）
   - 核心目标是什么？
   - 有哪些约束？

2. 识别依赖（30s）
   - 需要修改哪些文件？
   - 需要什么外部包？

3. 制定步骤（1min）
   - 分解为可验证的小步骤
   - 确定步骤顺序

深度设计流程

1. 需求分析（2min）
   - 功能需求
   - 非功能需求（性能、安全、可用性）
   - 边界条件

2. 架构设计（3min）
   - 组件划分
   - 接口定义
   - 数据流设计

3. 技术选型（2min）
   - 框架/库选择
   - 权衡分析

4. 实现规划（3min）
   - 详细步骤
   - 风险评估
   - 测试策略

输出格式

快速规划

# Plan: [功能名称]

## Goal
[一句话描述]

## Steps
1. [ ] [步骤 1]
2. [ ] [步骤 2]
3. [ ] [步骤 3]

## Files
- `path/to/file.ts` - [修改内容]

## Risk
- [主要风险] → [缓解策略]

深度设计

# Design: [系统/功能名称]

## Overview
[背景和目标]

## Architecture

### Components

┌─────────────┐ ┌─────────────┐ │ Component A │────▶│ Component B │ └─────────────┘ └─────────────┘


### Data Flow
[数据如何流动]

## Technical Decisions

### Decision 1: [名称]
- **Choice**: [选择]
- **Reason**: [原因]
- **Alternatives**: [备选方案]
- **Trade-offs**: [权衡]

## Implementation Plan

### Phase 1: [阶段名]
1. [ ] Step 1
2. [ ] Step 2

### Phase 2: [阶段名]
...

## Risks
| Risk | Impact | Mitigation |
|------|--------|------------|

## Success Criteria
- [ ] 标准 1
- [ ] 标准 2

设计原则

1. 简单优于复杂

能用简单方案就不要复杂化
避免过度设计
YAGNI - 不需要的就不做

2. 最小变更

优先复用现有代码
避免不必要的重构
保持向后兼容

3. 可测试性

每个步骤都可验证
定义清晰的成功标准
考虑自动化测试

常用设计模式

场景	推荐模式
数据访问	Repository
业务逻辑	Service Layer
对象创建	Factory
算法切换	Strategy
事件驱动	Observer
UI 组件	Compound Components

使用方式

# 快速规划（默认）
/plan

# 深度设计
/plan --deep

# 仅架构设计
/plan --arch

原则：好的设计是演进出来的。保持简单，按需扩展。先规划后动手。

Files

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.

metadata.yaml 457 B

Changes

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.

9d ago First seen · 191 lines · 0 tokens per session scan A b32ec4350577

Subscribe to this mod's changes

design-brain is a skill published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 929 tokens. 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.

Building agents Claude Code Planning agent-orchestration ai-agent ai-coding-assistant cli-tool codex-cli

codex-build

Orchestrate Codex to BUILD code in the background while this Claude Code session (typically Opus) plans and reviews — never babysitting. The session composes the implementation plan, kicks the dev-review runner detached via a background Bash task with --preset codex-build, ENDS ITS TURN, and is woken on exit to run a…

alanshurafa/co-evolution · 181 tokens

co-evolution

General-purpose co-evolution for questions, ideas, drafts, plans, specs, arguments, and markdown documents. Composes or bounces content between agents using [CONTESTED]/[CLARIFY] markers until it converges. Triggers on "co-evolution", "co-evolve", "co evolve", "bounce", "bounce document", "agent bouncer", "refine with…

alanshurafa/co-evolution · 118 tokens

recursive-task-optimizer

Build, configure, run, inspect, or troubleshoot agent-agnostic recursive improvement loops for a repository or artifact. Use when a task should be attempted repeatedly by Claude Code, Codex CLI, Hermes, or another CLI agent; when candidates must inherit mutable task instructions, a self-improving meta-procedure, and…

laruss/recursive-task-optimizer · 101 tokens

dev-review

Code-focused plan-bounce-execute workflow between Claude Code (Opus) and Codex CLI. Use when the user wants repo files changed, a bug fixed, a feature implemented, or a code plan verified before execution. One AI composes a plan, it bounces between agents with [CONTESTED]/[CLARIFY] markers until refined, then the…

alanshurafa/co-evolution · 176 tokens

cao-workflow

Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a…

awslabs/cli-agent-orchestrator · 79 tokens

aidlc-portfolio

Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…

awslabs/cli-agent-orchestrator · 74 tokens

sumulige-claude: Skill for Claude Code