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 agentmods add skills/dean0x/devflow/software-designnpx skills add dean0x/devflow --skill software-designgit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00072 | $0.01255 |
| Opus 5 | $0.00036 | $0.00628 |
| Sonnet 5 | $0.00014 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
software-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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Engineering Patterns
The canonical source of architectural patterns and principles for consistent, high-quality code.
Iron Law
NEVER THROW IN BUSINESS LOGIC [1][11]
All operations that can fail MUST return Result types. Exceptions are allowed ONLY at system boundaries (API handlers, database adapters). Any
throwstatement in business logic is a violation. No exceptions.
Philosophy
- Functional Core, Imperative Shell [11] — Pure business logic, side effects at boundary
- Explicit Error Handling [1][8] — Result types, no exceptions in business logic
- Immutability by Default [7][14] — Return new objects, never mutate
- Dependency Injection [3] — All deps injected, nothing instantiated internally
- Make Illegal States Unrepresentable [4][2] — Types enforce invariants at compile time
- Parse, Don't Validate [12] — Schema transforms at boundaries
Pattern 1: Result Types [1][5][6][18]
type Result<T, E = Error> = { ok: true; value: T } | { ok: false; error: E };
function createUser(data: unknown): Result<User, ValidationError> {
if (!valid(data)) return Err({ type: 'ValidationFailed', details: validate(data).errors });
return Ok(buildUser(data));
}
// Libraries: neverthrow [18], ts-results [19]. Theory: Moggi [5] + Wadler [6].
Pattern 2: Dependency Injection [3]
class UserService {
constructor(private db: Database, private emailer: EmailService) {}
// Test: new UserService(mockDb, mockEmailer) — never new Database() inside [3]
}
Pattern 3: Immutability [7][14]
// New object, never mutate input; copy before .sort() [7][14]
function updateUser(user: User, changes: Partial<User>): User {
return { ...user, ...changes };
}
Pattern 4: Functional Core, Imperative Shell [11]
// PURE CORE: no I/O, deterministic [11]
function calculateTotal(items: Item[], taxRate: number): number {
return items.reduce((sum, i) => sum + i.price, 0) * (1 + taxRate);
}
// IMPERATIVE SHELL: I/O at boundary only [11]
async function processOrder(id: string): Promise<Result<Order, Error>> {
const order = await db.getOrder(id);
return Ok(await db.save({ ...order, total: calculateTotal(order.items, 0.1) }));
}
What ships with it
6 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.
- 2d ago First seen · 144 lines · 72 tokens per session scan A e74d9dfbe92a
software-design is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,255 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
verify-change
变更校验关卡。分析代码变更,检测文档同步状态,评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。.
verify-security
安全校验关卡。自动扫描代码安全漏洞,检测危险模式,确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
gen-docs
文档生成器。自动分析模块结构,生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。.
verify-module
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。.