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-bytehouse-ai-querygit 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-bytehouse-ai-query)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-bytehouse-ai-query"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-bytehouse-ai-query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-bytehouse-ai-query"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-bytehouse-ai-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 85 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00144 | $0.02479 |
| Opus 5 | $0.00072 | $0.01239 |
| Sonnet 5 | $0.00029 | $0.00496 |
| Haiku 4.5 | $0.00014 | $0.00248 |
Grade B, and why
byted-bytehouse-ai-query scanned grade B with 2 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `jq`(`export_config.sh` 解析 JSON 需要,未安装时可 `brew install jq` 或 `sudo apt install jq`) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
sql_result = subprocess.run(cmd, capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
byted-bytehouse-ai-query
描述
ByteHouse AI Query Skill,提供以下核心能力:
- Text2SQL — 将自然语言查询需求转换为 ByteHouse SQL。
- List Tables — 列出目标数据库/实例下的所有库与表。
- Execute SQL — 执行 SQL 查询并返回结果,内置非 DQL 保护。
- 多模态向量化与检索 — 支持文本、图片、视频的向量化,以及向量/混合检索。
当以下情况时使用此 Skill:
- 用户希望通过自然语言查询 ByteHouse 中的数据("帮我查一下 xxx 表数据量"、"看看有哪些库和表" 等)。
- 用户明确要求把自然语言转成 SQL(Text2SQL),或需要在 ByteHouse 上执行 SQL。
- 用户希望在 ByteHouse 上进行文本/图片/视频的向量化存储与检索。
- 用户提到 ByteHouse、火山引擎云数仓、云原生数仓、数据仓库查询相关关键词。
🧭 智能体使用指引(重要)
Agent 在承接上述任务时,按以下流程调度本 Skill 内的脚本:
- 确保配置就绪:先执行
source scripts/export_config.sh,把~/.bytehouse_config.json中的配置注入环境变量。- 若
~/.bytehouse_config.json不存在或缺失BYTEHOUSE_HOST/BYTEHOUSE_PASSWORD,主动引导用户提供,并把用户返回的连接信息写入该 JSON 文件后再source。
- 若
- 摸清数据全貌:若用户没有明确指定库表,先使用
scripts/list_tables.py查询数据库/表列表,帮助用户/Agent 选定要查的表。 - 生成 SQL:需要把自然语言转成 SQL 时,使用
scripts/text2sql.py,将目标表以位置参数传入。 - 执行 SQL:拿到 SQL 后使用
scripts/execute_sql.py。默认只允许执行 DQL,非 DQL(INSERT/UPDATE/DROP 等)需要先向用户确认再附加--force。 - 多模态检索场景:使用
scripts/embedding.py+scripts/search_client.py完成向量化与向量/混合检索。 - 展示结果:默认返回前 5 条结果,异常时展示完整报错。任何时候都要对密钥、密码等敏感字段做 Mask。
Agent 必须通过上述脚本发起查询/执行,不允许自行拼装 SQL 或直接连接 ByteHouse。
📁 文件说明
- SKILL.md — 本文件,技能主文档。
- requirements.txt — Python 依赖列表。
- scripts/text2sql.py — Text2SQL 转换脚本。
- scripts/list_tables.py — 列出数据库或指定库下的表。
- scripts/execute_sql.py — 执行 SQL 查询脚本,内置 DQL 保护。
- scripts/client.py — ByteHouse 连接客户端通用模块。
- scripts/embedding.py — 多模态向量化脚本。
- scripts/search_client.py — ByteHouse 向量检索客户端。
- scripts/export_config.sh — 从
~/.bytehouse_config.json加载配置到环境变量(依赖jq)。
配置说明
配置文件位于 ~/.bytehouse_config.json。如果文件存在且非空,直接使用文件中的配置;否则,向用户询问必填连接信息(可以把这份文档发给用户以便查阅 ByteHouse 连接信息获取指引),拿到后写入 JSON 文件,避免重复询问。当用户切换 ByteHouse 集群时,一并更新该文件。
{
"BYTEHOUSE_HOST": "<ByteHouse-host>",
"BYTEHOUSE_PORT": "8123",
"BYTEHOUSE_USER": "bytehouse",
"BYTEHOUSE_PASSWORD": "<ByteHouse-password>",
"BH_ARK_API_KEY": "<火山引擎方舟 API 密钥>",
"BH_ARK_BASE_URL": "https://ark.cn-beijing.volces.com/api/v3",
"BH_EMBEDDING_MODEL": "doubao-embedding-vision-251215"
}
What ships with it
9 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.
- LICENSE 633 B
- requirements.txt 116 B
- scripts/client.py 3.3 KB runs code
- scripts/embedding.py 5.9 KB runs code
- scripts/execute_sql.py 3.4 KB runs code
- scripts/export_config.sh 540 B runs code
- scripts/list_tables.py 2.5 KB runs code
- scripts/search_client.py 17 KB runs code
- scripts/text2sql.py 7.5 KB runs code
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.
- 9d ago First seen · 221 lines · 144 tokens per session scan B 27769ac4a76b
byted-bytehouse-ai-query is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 5d ago), licensed Apache-2.0. It adds 144 tokens to every session and 2,479 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bigquery-ai-ml
Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).
local-embedding
Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.
azure-horizondb
Expert knowledge for Azure Horizondb development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using azureai SQL/embeddings, pgvector tuning, Apache AGE graphs, hybrid…
azure-documentdb
Expert knowledge for Azure DocumentDB development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using DocumentDB search (BM25/vector), Data API, MongoDB compatibility, change…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
vector-db-ops
Use when vector database operations — Pinecone, Weaviate, Qdrant, ChromaDB. Indexing, querying, filtering, and managing vector embeddings for RAG and similarity search. Use when working with vector db ops.