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-deepsearchgit 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-deepsearch)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-deepsearch"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-deepsearch.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 | $0.00105 | $0.02127 |
| Opus 5 | $0.00053 | $0.01064 |
| Sonnet 5 | $0.00021 | $0.00425 |
| Haiku 4.5 | $0.00011 | $0.00213 |
Grade A, and why
byted-deepsearch 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 6d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BytedDeepsearch
概述
深度研究代理系统社区版是一个基于工作流的深度研究系统，能够对复杂主题进行多轮迭代的网络搜索和综合分析。系统通过结合LLM智能分析和实时网络搜索，生成详细的研究报告。
依赖技能
工作流调用逻辑
系统架构
本系统是一个工作流描述文档，没有执行脚本。依赖以下外部技能：
- byted-web-search skill: 执行网页搜索`
- LLM技能: 用于智能分析和推理
工作流程
1. 输入接收阶段
- 用户输入: 研究主题（sys.query）和研究深度（depth）
- 默认深度: 3（可配置）
2. 初始化阶段
- 创建迭代数组，深度为指定的depth值
- 数组格式：
[0, 1, ..., depth-1]
3. 迭代搜索阶段（多轮执行）
每轮迭代执行以下步骤：
a) LLM智能分析
- 使用LLM分析当前研究状态
- 输入：用户查询、已收集的findings、已搜索的topics
- 输出：JSON格式，包含：
nextSearchTopic: 下一个搜索主题（字符串或None）shouldContinue: 是否继续搜索（布尔值）
b) JSON解析
- 提取
nextSearchTopic和shouldContinue字段 - 更新对话变量
c) 条件判断
- 如果
shouldContinue为True：- 执行byted-web-search：
python scripts/web_search.py "<nextSearchTopic>" - 将搜索结果追加到findings数组
- 更新搜索进度显示
- 继续下一轮迭代
- 执行byted-web-search：
- 如果
shouldContinue为False：- 结束当前迭代
- 输出中间结果
d) 变量管理
- 更新
nextSearchTopic和shouldContinue变量 - 将
nextSearchTopic追加到topics数组（记录已搜索主题） - 避免重复搜索相同主题
4. 综合分析阶段
- 所有迭代完成后，使用LLM综合分析所有收集到的findings
- 生成详细的综合分析报告
- 输出格式：Markdown格式的详细报告
5. 报告生成阶段
- 输出最终的研究分析结果
- 包含重要洞察、结论和剩余不确定性
- 适当引用来源
变量说明
系统维护以下对话变量：
| 变量名 | 类型 | 描述 |
|---|---|---|
topics |
array[string] | 已搜索的主题列表 |
nextSearchTopic |
string | 下一个要搜索的主题 |
findings |
array[string] | 收集到的搜索结果列表 |
shouldContinue |
string | 是否继续搜索的标志 |
网页搜索集成
当需要进行网络搜索时：
- 使用
nextSearchTopic作为查询参数 - 运行byted-web-search技能：
python scripts/web_search.py "<query>" - 根据返回的摘要列表组织答案，不新增或臆造内容
- 将搜索结果追加到
findings数组
注意: 不要使用任何搜索参数配置（如search_depth、topic、max_results、country、time_range、days等），仅保留核心输入query。
进度跟踪
系统实时显示搜索进度：
- 格式：
{index + 1}/{depth}th search executed. - 例如：
1/3th search executed.
使用场景
适用场景
- 复杂主题研究: 需要对特定主题进行深入、全面的研究
- 最新信息分析: 需要基于最新网络信息生成详细分析报告
- 多角度探索: 需要从不同角度和维度探索一个主题
- 系统化调查: 需要系统化的调查和证据收集
典型用例
- 市场趋势分析
- 技术发展研究
- 竞争对手分析
- 学术文献综述
- 产品调研
技术特点
智能特性
What ships with it
1 file 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.
- 6d ago First seen · 246 lines · 105 tokens per session scan A 02e019889b2e
byted-deepsearch is a skill published in the GitHub repository bytedance/agentkit-samples (449 stars, last pushed 3d ago), licensed Apache-2.0. It adds 105 tokens to every session and 2,127 once invoked, about $0.0005 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.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.