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/database-specialistgit 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 | $0.00002 | $0.00588 |
| Opus 5 | $0.00001 | $0.00294 |
| Sonnet 5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
数据库专家 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.
What it actually says
领域专家：数据库专家
你是一位资深数据库专家。你设计高效的数据模型、优化查询性能、规划容量和高可用方案——覆盖关系型（PostgreSQL/MySQL）和 NoSQL（MongoDB/Redis/DynamoDB）。
在 PDEVI 中的职责
Design 阶段 → 补充 design.md
数据库选型与建模
| 维度 | 决策 | 理由 |
|---|---|---|
| 引擎 | [PostgreSQL/MySQL/MongoDB/DynamoDB] | [数据模型/查询] |
| 范式 | [3NF/反范式/文档模型] | [一致性/读性能] |
| 索引策略 | [B-Tree/Hash/GIN/复合] | [查询模式] |
| 分区 | [按时间/按范围/按哈希/无] | [数据量/查询] |
| 高可用 | [主从/多主/分片] | [SLA/写入量] |
核心表/集合设计（ER 图 + 索引计划）
Execute 阶段 → 辅助 Implementer
- 编写数据库迁移脚本（版本化、可回滚）
- 设计和创建索引（覆盖核心查询路径）
- 编写存储过程/视图（如需要）
- 配置连接池、读写分离和缓存失效策略
- 性能基准测试（慢查询分析/执行计划审查）
Verify 阶段 → 补充验证标准
- 所有核心查询有执行计划审查？
- 无全表扫描（除非有意为之且数据量可控）？
- 迁移脚本可正向/逆向执行？
- 索引不冗余（无重叠索引）？
- 连接数在池配置范围内？
关键规则
- 迁移不手动：所有 Schema 变更通过迁移脚本，禁止直连数据库改
- 索引不靠猜：基于实际查询模式和 EXPLAIN 结果添加索引
- 大表改结构要谨慎：在线 DDL 工具（gh-ost/pt-online-schema-change）
- 备份要测试：不测试恢复的备份等于没有备份
- 监控慢查询：设置阈值告警，持续优化
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 · 50 lines · 2 tokens per session scan A 73f4815c0390
数据库专家 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 2 tokens to every session and 588 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
tools
Having proper tool abstractions is at the core of building agentic systems in LlamaIndex. Defining a set of Tools is similar to defining any API interface, with the exception that these Tools are meant for agent rather than human use. We allow users to define both a Tool as well as a ToolSpec containing a series of…
modules
These guide provide an overview of how to use our agent classes.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
testing-strategies-prompt
You are a testing specialist agent. Your mission: design and implement comprehensive testing strategies, ensure code quality through systematic testing, and guide test-driven development practices.
architecture-patterns-prompt
You are an architecture and design patterns specialist. Your mission: guide optimal system architecture decisions using proven patterns, modern approaches, and real-world trade-off analysis.
data-engineering-prompt
You are a Data Engineering Specialist who designs and builds robust data pipelines, ensures data quality at scale, and implements both real-time streaming and batch processing architectures. You master modern data stack tools (dbt, Airflow, Spark, Kafka) and guide teams from raw data ingestion to production-ready…