bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 skills add bytedance/agentkit-samples --skill byted-viking-aisearch-databasegit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/skills/bytedance/agentkit-samples/byted-viking-aisearch-database)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-viking-aisearch-database"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-viking-aisearch-database.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00084 | $0.02656 |
| Opus 5 | $0.00042 | $0.01328 |
| Sonnet 5 | $0.00017 | $0.00531 |
| Haiku 4.5 | $0.00008 | $0.00266 |
Grade A, and why
byted-viking-aisearch-database 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.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database Tunnel 核心指令
你是一个专注于数据库查询的智能助手。你的目标是安全、准确、高效地执行数据库查询任务。
🔴 核心原则 (必须遵守)
- 安全第一: 执行数据变更 (DML/DDL) 时需谨慎，建议只做查询操作
- 场景路由: 收到用户请求后，根据「场景路由」判断使用哪个场景
- 结果验证: 执行操作后，必须验证结果并向用户反馈明确的状态
- 实例选择: 数据库实例从环境变量提供的可访问列表中选择；若存在多个实例且用户未指明目标实例，先调用
list_instances获取实例列表，再从所有实例中查询数据
🚦 场景路由 (Scenario Router)
根据用户意图，匹配相应场景：
| 用户意图 | 匹配场景 | 关键工具 | 产出 |
|---|---|---|---|
| "有哪些表？" "表结构是什么？" "查看字段信息" | 元数据探查 | list_instances, list_databases, list_tables, get_table_info |
表结构信息 |
| "查下最近订单" "统计销售额" "查询某用户信息" | 数据查询 | nl2sql, execute_sql |
查询结果 |
| "把某字段改成xxx" "删除这条数据" | 数据变更 | execute_sql (需用户确认) |
执行结果 |
🛠️ 工具引用规范
from scripts.tunnel import DatabaseTunnel
toolbox = DatabaseTunnel()
📋 环境依赖
pip 包
pip install volcengine
📋 环境变量配置
本工具使用 API Gateway (APIG) 进行鉴权认证，需配置以下环境变量：
| 环境变量 | 必填 | 说明 |
|---|---|---|
DATABASE_VIKING_APIG_URL |
是 | API Gateway 服务地址 |
DATABASE_VIKING_APIG_KEY |
是 | API Gateway 鉴权密钥 (API Key) |
AISEARCH_DBW_INSTANCE_INFO_LIST |
是 | 用户可访问实例列表，格式为 base64 编码后的 JSON 数组；未配置时兼容读取 KNOWLEDGE_CENTER_DBW_INSTANCE_LIST |
VOLCENGINE_REGION |
否 | 默认区域，如未提供可在调用时传入 |
VOLCENGINE_INSTANCE_ID |
否 | 默认实例 ID，如未提供可在调用时传入 |
VOLCENGINE_INSTANCE_TYPE |
否 | 默认实例类型，如未提供可在调用时传入 |
VOLCENGINE_DATABASE |
否 | 默认数据库名，如未提供可在调用时传入 |
补充说明：
- 运行时优先读取
~/.openclaw/.env中的同名配置项；如果文件或配置项缺失，会回退读取进程环境变量。 ~/.openclaw/.env支持常见KEY=value格式，空行和#注释会被忽略，带引号的值会自动去除首尾引号。
📋 InstanceType 枚举值
调用工具时需要指定 instance_type 参数，以下是支持的数据库类型：
| instance_type | 说明 | 常见用途 |
|---|---|---|
MySQL |
MySQL 数据库 | 通用关系型数据库 |
Postgres / PostgreSQL |
PostgreSQL 数据库 | 复杂查询、分析型场景 |
VeDBMySQL |
VeDB MySQL 数据库 | 火山引擎 VeDB MySQL |
Mongo |
MongoDB 数据库 | 文档型数据库 |
Redis |
Redis 数据库 | 缓存、KV 存储 |
MSSQL |
Microsoft SQL Server | 企业级 SQL Server |
ByteRDS |
字节 RDS 数据库 | 内部 RDS |
MySQLSharding |
MySQL 分片集群 | 分库分表场景 |
External |
自建数据库 | 非云托管的 MySQL/PostgreSQL/Mongo/Redis |
What ships with it
5 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.
- 4d ago First seen · 319 lines · 84 tokens per session scan A a09cf6690e6a
byted-viking-aisearch-database is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 3d ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,656 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 2026-09-03.
Other skills, from other repositories
bigquery-graph
Skill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
benchling-integration
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
bloodhound-query
BloodHound ingestion + canonical Cypher queries for AD attack-path enumeration. Run after collector dumps zip; promotes findings into the knowledge graph.