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 commands/infra403/agentic-engineering-lab/architecture-designgit clone --depth 1 https://github.com/infra403/agentic-engineering-labWrote 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/commands/infra403/agentic-engineering-lab/architecture-design)<a href="https://agentmods.dev/commands/infra403/agentic-engineering-lab/architecture-design"><img src="https://agentmods.dev/badge/commands/infra403/agentic-engineering-lab/architecture-design.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 | $0.00077 | $0.00787 |
| Opus 5 | $0.00039 | $0.00394 |
| Sonnet 5 | $0.00015 | $0.00157 |
| Haiku 4.5 | $0.00008 | $0.00079 |
Grade A, and why
architecture-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 4d 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.
What it actually says
/architecture-design 命令
从 checkpoint-2（领域模型）出发，完成架构设计、技术规格、设计评审三个阶段。
工作流
阶段 3：架构设计（Architecture Design）
- 上下文重置 — 仅依赖 checkpoint-2
- 读取
.claude/skills/architecture-design/SKILL.md - 读取
.claude/skills/architecture-design/references/PROTOCOL.md - 加载
.claude/skills/architecture-design/knowledge/architecture-styles.md - 加载
.claude/skills/architecture-design/knowledge/data-systems.md - 如有消息集成需求 → 加载
knowledge/integration-patterns.md（如存在） - 激活
.claude/skills/architecture-design/roles/system-architect.md作为 Generator - 激活
.claude/skills/architecture-design/roles/reviewer.md作为 Evaluator - 走收敛循环 GENERATE → EVALUATE → RESOLVE → CHECK
- 产出 checkpoint-3-architecture.yaml
阶段 4：技术规格（Technical Specification）
- 上下文重置 — 仅依赖 checkpoint-3
- 加载
.claude/skills/architecture-design/knowledge/security-patterns.md - 不加载新架构知识 — 引用 checkpoint-3 中已确定的 [K]
- 激活 system-architect 作为 Generator
- 激活 reviewer 作为 Evaluator
- 走收敛循环
- 产出 checkpoint-4-specification.yaml
阶段 5：设计评审（Design Review）
- 上下文重置 — 依赖 checkpoint-1 到 checkpoint-4
- 不预加载知识文件 — 按需 Read 验证 [K] 引用
- 激活 reviewer 作为主导角色
- 执行四维评审（纵向一致性 + 横向一致性 + 知识锚定 + 盲点检测）
- 产出 checkpoint-5-review.yaml
使用方式
/architecture-design — 从阶段 3 开始完整流程（3→4→5）
/architecture-design 架构设计 — 仅执行阶段 3（需已有 checkpoint-2）
/architecture-design 技术规格 — 仅执行阶段 4（需已有 checkpoint-3）
/architecture-design 设计评审 — 仅执行阶段 5（需已有 checkpoint-1~4）
产出物
checkpoint-3-architecture.yaml— 架构方案 + ADR + 技术选型checkpoint-4-specification.yaml— DDL + API 规格 + 部署配置 + 成本估算checkpoint-5-review.yaml— 评审报告 + 追溯矩阵 + 技术债清单- 更新
design-progress.json
前置条件
- checkpoint-2-modeling.yaml 已存在（由
/product-design 领域建模产出）
后续
完成设计评审后，使用 /implement 命令开始 Spec-Driven Incremental Deploy。
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.
- 4d ago First seen · 67 lines · 77 tokens per session scan A 49cc5aa5601e
architecture-design is a command published in the GitHub repository infra403/agentic-engineering-lab (5 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 787 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.