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-knowledge-base-managementgit 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-knowledge-base-management)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-bytehouse-knowledge-base-management"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-bytehouse-knowledge-base-management/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-knowledge-base-management"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-bytehouse-knowledge-base-management.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00913 |
| Opus 5 | $0.00015 | $0.00456 |
| Sonnet 5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
byted-bytehouse-knowledge-base-management 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 8d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
byted-bytehouse-knowledge-base-management
描述
ByteHouse Knowledge Base Management，提供 ByteHouse 知识库的管理能力，包括创建知识库、添加知识库内容、查询知识库
📁 文件说明
- SKILL.md - 本文件，技能主文档
- create_knowledge_base.py - 创建知识库脚本
- recall_knowledge_base.py - 知识库文件召回脚本
- upload_file_to_kb.py - 上传文件到知识库脚本(pdf/md/docx/xlsx)
- delete_file_from_kb.py - 删除知识库内容脚本
- delete_knowledge_base.py - 删除知识库脚本
- list_files_in_kb.py - 查询知识库文件列表脚本
- list_knowledge_base.py - 查询知识库列表脚本
- knowledge_base_chat.py - 知识库流式问答脚本
配置说明
配置保存在 ~/.bytehouse_config.json ，如果该文件存在且非空，则直接使用文件中的配置。如果不存在，则让用户提供ByteHouse连接信息（ 把这个文档也发给用户，文档里面介绍了如何获取主机地址和密码：https://www.volcengine.com/docs/6517/1121919?lang=zh ）。用户提供信息后，保存到json文件，避免重复向用户请求连接信息。当用户切换ByteHouse集群时，一并修改该文件。
{
"BYTEHOUSE_HOST": "<ByteHouse-host>",
"BYTEHOUSE_PASSWORD": "<ByteHouse-password>"
}
BYTEHOUSE_HOST（主机地址）和BYTEHOUSE_PASSWORD（密码）必须由用户提供
执行 scripts/export_config.sh 把配置信息导入环境变量中
source scripts/export_config.sh
风险预警
当用户希望删除知识库中的某个文件，或者删除整个知识库时，必须提示用户数据不可恢复，向用户再次确认后再执行。
前置条件
- Python 3.8+
- uv (已安装在
/root/.local/bin/uv)
🚀 使用方法
以下是每个脚本的具体使用指令示例。在执行这些脚本前，请确保已经导入了配置：
# 导入配置
source scripts/export_config.sh
1. 创建知识库 (create_knowledge_base.py)
python3 scripts/create_knowledge_base.py "我的知识库"
# 可选参数：--description "这是我的知识库描述"
2. 查询知识库列表 (list_knowledge_base.py)
python3 scripts/list_knowledge_base.py
3. 上传文件到知识库 (upload_file_to_kb.py)
python3 scripts/upload_file_to_kb.py --kb-id 123 --file ./document.pdf
# 可选参数：--chunk-size 512 --delimiters "#,##" --enable-image-ocr --enable-chunk-auto-merge
4. 查询知识库文件列表 (list_files_in_kb.py)
python3 scripts/list_files_in_kb.py --kb-id 123
5. 知识库文件召回 (recall_knowledge_base.py)
python3 scripts/recall_knowledge_base.py --kb-id 123 --query "你的搜索问题"
6. 知识库流式问答 (knowledge_base_chat.py)
python3 scripts/knowledge_base_chat.py --kb-ids 123 --input "你的提问"
What ships with it
10 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
- scripts/create_knowledge_base.py 5.5 KB runs code
- scripts/delete_file_from_kb.py 3.4 KB runs code
- scripts/delete_knowledge_base.py 3.3 KB runs code
- scripts/export_config.sh 540 B runs code
- scripts/knowledge_base_chat.py 5.0 KB runs code
- scripts/list_files_in_kb.py 3.4 KB runs code
- scripts/list_knowledge_base.py 3.0 KB runs code
- scripts/recall_knowledge_base.py 5.4 KB runs code
- scripts/upload_file_to_kb.py 9.3 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.
- 8d ago First seen · 97 lines · 31 tokens per session scan A a07614bbadd3
byted-bytehouse-knowledge-base-management is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 4d ago), licensed Apache-2.0. It adds 31 tokens to every session and 913 once invoked, about $0.0002 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 skills, from other repositories
sensitive-information-disclosure
Hunt LLM sensitive-information disclosure (OWASP LLM02:2025) — leakage of PII, secrets, internal source, model details, and other-tenant data through model outputs, training-data extraction, or retrieval-side joins.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
aatmf-t12-rag-poisoning
AATMF T12 — RAG & Knowledge Base Manipulation. PoisonedRAG, vector store flood, embedding collision, retrieval-bias attacks.
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
unified-llm-api
Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.