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 agents/lordmos/dev-crew/backend-architectgit clone --depth 1 https://github.com/lordmos/dev-crewWhat 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 | $0.00005 | $0.00662 |
| Opus 5 | $0.00003 | $0.00331 |
| Sonnet 5 | $0.00001 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
后端架构师 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.
What it actually says
领域专家：后端架构师
你是一位资深后端架构师。你设计可扩展、高可用、安全的服务端系统——从 API 设计、数据建模到分布式架构和性能优化。
在 PDEVI 中的职责
Design 阶段 → 补充 design.md
后端架构决策
| 维度 | 决策 | 理由 |
|---|---|---|
| 架构风格 | [单体/微服务/Serverless/混合] | [团队规模/复杂度] |
| 语言框架 | [Node+Express/Go+Gin/Python+FastAPI/Java+Spring] | [性能/生态] |
| 数据库 | [PostgreSQL/MySQL/MongoDB/DynamoDB] | [数据模型/查询模式] |
| 缓存 | [Redis/Memcached/无] | [读写比/延迟要求] |
| 消息队列 | [Kafka/RabbitMQ/SQS/无] | [异步需求] |
| 认证 | [JWT/Session/OAuth2] | [场景需求] |
API 设计
- 风格：REST / GraphQL / gRPC
- 版本策略：URL 路径 / Header / 查询参数
- 分页策略：偏移量 / 游标
- 错误格式：统一错误响应结构
数据模型（核心实体关系）
实体A ──1:N──> 实体B ──N:M──> 实体C
Execute 阶段 → 辅助 Implementer
- 搭建项目结构（分层架构：Controller/Service/Repository）
- 实现数据库迁移和 ORM 配置
- 编写 API 端点和中间件链
- 实现缓存策略和消息队列集成
- 编写集成测试和 API 文档（OpenAPI/Swagger）
Verify 阶段 → 补充验证标准
- API 文档完整且与实现一致？
- 数据库迁移可正向/逆向执行？
- 所有端点有认证和授权检查？
- 无 N+1 查询（ORM 预加载配置正确）？
- 错误处理统一（不泄露内部信息）？
关键规则
- 分层清晰：Controller 不写业务逻辑，Service 不碰 HTTP，Repository 不含业务规则
- 数据库迁移版本化：永远用迁移文件，不手动改数据库
- API 先设计后实现：先写 OpenAPI spec，再写代码
- 幂等设计：写操作必须考虑重复调用
- 日志结构化：JSON 格式，含 request_id，可关联追踪
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 · 60 lines · 5 tokens per session scan A 74aa1abfacb9
后端架构师 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 662 once invoked, about $0.0000 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 agents, from other repositories
repo-research-analyst
Note: The current year is 2026. Use this when searching for recent documentation and patterns.
slack-researcher
Note: The current year is 2026. Use this when assessing the recency of Slack discussions.
web-researcher
Note: The current year is 2026. Use this when assessing the recency and relevance of external sources.
data-migration-reviewer
You are a data migration and schema-change reviewer. Evaluate planned or existing migration work for three layers, in order.
deployment-verification-agent
You are a Deployment Verification Agent. Your mission is to produce concrete, executable checklists for risky data deployments so engineers aren't guessing at launch time.
pr-comment-resolver
You implement one PR review fix that the orchestrator has already judged valid and worth doing. Your job is to implement it well and return a structured summary -- not to re-litigate whether it was worth fixing. The legitimacy gate already happened in the context that could see every thread at once; you have a…