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/architecturenpx skills add dean0x/devflow --skill architecturegit 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 | $0.00022 | $0.01349 |
| Opus 5 | $0.00011 | $0.00674 |
| Sonnet 5 | $0.00004 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
architecture 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 yesterday.
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Patterns
Domain expertise for software architecture and design pattern analysis. Full bibliography: references/sources.md.
Iron Law
SEPARATION OF CONCERNS IS NON-NEGOTIABLE [1][2]
Every module has one reason to change. Every layer has clear boundaries. Every dependency points in one direction. Parnas (1972): decompose by information hiding, not by task. Violations compound into unmaintainable systems. [1][19]
SOLID Violations [2]
SRP — One class, one reason to change. [1][2][8]
VIOLATION: UserController handles HTTP + validation + DB + email
CORRECT: Inject UserService, UserValidator — each class has one reason to change
OCP — Extend without modifying. [2]
VIOLATION: if (type === 'credit') ... else if (type === 'paypal') ...
CORRECT: Strategy pattern — new payment = new class, existing code unchanged
LSP — Subtypes must be substitutable. [3] Liskov & Wing (1994): subtype cannot strengthen preconditions. Throwing where parent doesn't throw is a violation.
VIOLATION: ReadOnlyStorage extends FileStorage { write() { throw new Error(...) } }
CORRECT: Segregated interfaces (Readable, Writable) — compile-time, not runtime
ISP — No forced unused implementations. [2]
VIOLATION: interface Worker { work(); eat(); sleep(); } // Robot forced to implement eat()
CORRECT: interface Workable { work(): void; } — implement only what you support
DIP — Depend on abstractions, not concretions. [2][18] Fowler (2004): constructor injection is the cleanest form. [18]
// VIOLATION: class OrderService { private db = new PostgresDatabase(); }
// CORRECT: class OrderService { constructor(private repo: OrderRepository) {} }
Coupling Issues [8][17]
Stevens, Myers & Constantine (1974): content coupling (direct instantiation) is the tightest and worst form. [8]
Tight Coupling [8][18]: Direct instantiation — can't mock, can't swap.
VIOLATION: class ReportGenerator { generate() { new DatabaseService().query(...) } }
CORRECT: Inject dependencies via constructor
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.
- yesterday First seen · 139 lines · 22 tokens per session scan A 531f51179aad
architecture is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,349 once invoked, about $0.0001 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。.