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 agentmods add skills/bytedance/agentkit-samples/byted-data-searchnpx skills add bytedance/agentkit-samples --skill byted-data-searchgit 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-data-search)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-data-search"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-data-search.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00358 | $0.04317 |
| Opus 5 | $0.00179 | $0.02159 |
| Sonnet 5 | $0.00072 | $0.00863 |
| Haiku 4.5 | $0.00036 | $0.00432 |
Grade A, and why
byted-data-search 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 5d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数据查询工具
前置要求
需要环境变量（脚本会自动读取，若读取不到需提醒用户设置）：
VOLCENGINE_ACCESS_KEY（或VOLC_ACCESS_KEY）VOLCENGINE_SECRET_KEY（或VOLC_SECRET_KEY）
工作流程（严格按顺序执行）
第一步：查询可用数据源（必须先执行）
在构造任何查询之前，必须先调用此步骤了解有哪些数据源及其字段定义。这一步的作用是：确认用户需要的数据存在于哪个数据源中，以及该数据源有哪些字段和过滤规则。跳过这一步直接去猜字段名几乎一定会出错。
# 列出所有可用数据源摘要（含 datasource_id、名称、描述、维度/过滤字段数量）
python3 scripts/describe_datasource.py --datasource-id all
# 获取某个数据源的完整字段定义（维度 dimensions、字段类型、可用过滤操作符）
python3 scripts/describe_datasource.py --datasource-id <数据源ID>
返回内容包含：
datasource_id：数据源唯一标识datasource_name：数据源中文名称description：数据源说明dimensions：所有字段列表，每个字段包含 field（字段名）、label（显示名）、type（类型）、description（描述）、filterable（是否可作为过滤条件字段）notes：使用备注
关键：根据返回的字段信息（尤其是 field 名称和 type 类型），确定需要用到的字段和过滤操作符，再进入第二步。
字段类型与操作符对照表
每种字段类型只支持特定操作符。用错操作符会直接报错，所以在构造 filters 之前请务必对照此表。
| 字段类型 | 支持的操作符 | 说明 |
|---|---|---|
keyword |
eq, in, not_in |
精确匹配类字段（如编码、状态、类型） |
text |
like, keyword |
文本类字段（如名称、地址、描述），支持模糊搜索 |
date / datetime |
between, eq |
日期类字段，范围查询用 between |
long / integer / float / double |
range, eq |
数值类字段，范围查询用 range |
注意：
long类型字段如企业标签（is_longtou_flag等）虽然是数值类型，但用于布尔判断时用eq即可，如is_longtou_flag:eq:1。
字段取值不确定时：先探查再过滤
构造过滤条件时，经常会遇到"知道要按某个字段过滤，但不确定该字段的实际取值是什么"的情况。比如用户想按企业状态筛选，但不知道取值是"存续"、"在业"还是"正常"；或者想按产业分类过滤，但不确定分类名称的准确写法。
正确做法：先做一次不带该过滤条件（或只带其他确定条件）的查询，从返回数据中观察目标字段的实际取值，再用准确的值构造过滤条件。
具体步骤：
- 先用宽松条件查询几条数据，观察目标字段返回了哪些值
- 如果需要看该字段有哪些不同取值，可以用
--group-by+--aggregation做分组统计 - 确认取值后，再加上精确的过滤条件做正式查询
示例——想按"企业状态"过滤但不确定取值：
# 第 1 步：先查几条数据，观察 reg_status 字段的实际值
python3 scripts/query_datasource.py \
--datasource-id enterprise_basic_wide \
--filters 'company_name:like:科技'
# 第 2 步：或者直接做分组统计，看 reg_status 有哪些取值及各有多少条
python3 scripts/query_datasource.py \
--datasource-id enterprise_basic_wide \
--filters 'company_name:like:科技' \
--group-by 'reg_status' \
--aggregation 'company_id:count'
# 第 3 步：确认取值后，加上精确过滤条件
python3 scripts/query_datasource.py \
--datasource-id enterprise_basic_wide \
--filters 'company_name:like:科技;reg_status:eq:存续'
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.
- 5d ago First seen · 340 lines · 358 tokens per session scan A acd9b8c5be9f
byted-data-search is a skill published in the GitHub repository bytedance/agentkit-samples (446 stars, last pushed yesterday), licensed Apache-2.0. It adds 358 tokens to every session and 4,317 once invoked, about $0.0018 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
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
sn-image-imitate
Generates a new image that imitates the style of a reference image while updating content based on user intent. Uses a three-stage pipeline: image annotation (long caption), caption rewriting, and image generation. Use when user asks to "imitate style", "保持这个风格重画", "按这张图风格生成", or "style transfer with new content".
akg-agents
代理执行 AKG 算子任务。先检查固定仓库与分支；若 /.akg/checkenv.md 不存在则强制 FULLSETUP=true；忽略所有 akgcli 检查和使用；后端代码生成直接执行 runworkflow.py --workflow kernelgen。.