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-volcengine-finopsgit 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-volcengine-finops)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-volcengine-finops"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-volcengine-finops.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 | $0.00082 | $0.04120 |
| Opus 5 | $0.00041 | $0.02060 |
| Sonnet 5 | $0.00016 | $0.00824 |
| Haiku 4.5 | $0.00008 | $0.00412 |
Grade A, and why
byted-volcengine-finops 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
火山引擎账单 Skill
这个 Skill 用于通过火山引擎 Python SDK 查询费用中心账单数据，并围绕账期、分摊月、日期、实例、产品、账号、分账维度做汇总分析。
何时使用此 Skill
当用户要求：
- 分析火山引擎账单、成本和消费趋势的时候
- 查询账号维度账单总览信息的时候
- 查询产品维度成本分布的时候
- 核对账单明细、实例费用或账单类型的时候
- 查询分摊后成本、摊销成本或成本账单明细的时候
- 查询分账账单、分拆项费用或分摊结果的时候
主要功能
1. 账号账单总览查询
- 使用
ListBillOverviewByCategory查询账号维度账单总览 - 适合先看整月整体账单金额和大盘趋势
2. 产品月度账单查询
- 使用
ListBillOverviewByProd查询单产品、多产品、全量产品月度账单 - 支持分页获取完整产品列表
- 适合识别高成本产品和主要费用来源
3. 账单明细与分账查询
- 使用
ListBillDetail查询账单明细 - 使用
ListAmortizedCostBillDetail查询成本账单明细 - 使用
ListSplitBillDetail查询分账账单 - 支持按账期、分摊月、日期、产品、账号、实例、分拆项筛选
4. 配置与调用方式
- 支持环境变量配置
AK/SK - 支持
.env文件配置 - 支持 Python 代码调用
- 支持通过
scripts/下的独立脚本直接调用 - 支持分页拉取与本地汇总分析
- 支持 JSON 结构化结果处理
处理逻辑
账单查询处理流程
- 根据用户目标确定接口
- 整体账单使用
ListBillOverviewByCategory - 产品月度账单使用
ListBillOverviewByProd - 明细核对使用
ListBillDetail - 成本明细使用
ListAmortizedCostBillDetail - 分账排查使用
ListSplitBillDetail
- 整体账单使用
- 根据时间要求确定账期与日期范围
- 优先确定
BillPeriod - 成本账单优先确定
AmortizedMonth - 需要单日细查时补充
ExpenseDate - 成本账单按日细查时补充
AmortizedDay - 跨月查询需要拆成多个账期分别查询
- 优先确定
- 根据过滤条件组装 SDK 请求参数
- 例如产品、账号、实例、账单类型、分拆项等
- 如为分页接口则循环查询
- 使用
Offset + Limit + NeedRecordNum分页拉全量 - 可使用
common.py中的fetch_all_pages工具函数自动翻页
- 使用
- 对结果做汇总分析
- 输出金额、排行、异常波动和待核对项
前置要求
需要安装火山引擎 Python SDK：
pip install --upgrade "volcengine-python-sdk>=5.0.30"
说明：
- 建议使用 5.x 最新版本
- 历史版本
4.0.1 ~ 4.0.42存在 SDK 重试缺陷，尽量不要继续使用
配置方式
需要配置火山引擎的 Access Key 和 Secret Key。推荐使用以下两种方式之一：
方式 1：环境变量
export VOLCENGINE_AK="your-ak"
export VOLCENGINE_SK="your-sk"
export VOLCENGINE_REGION="cn-beijing"
方式 2：.env 文件
在 ~/.openclaw/workspace/.env 中配置：
VOLCENGINE_AK=your-ak
VOLCENGINE_SK=your-sk
VOLCENGINE_REGION=cn-beijing
账单参数说明
账单查询核心参数
- BillPeriod: 账务账期，格式为
YYYY-MM - ExpenseDate: 账单日期，格式为
YYYY-MM-DD - AmortizedMonth: 分摊月，格式为
YYYY-MM - AmortizedDay: 分摊日，格式为
YYYY-MM-DD - Offset: 分页偏移量
- Limit: 单页数量，范围
[1,300] - NeedRecordNum: 是否返回总记录数，
1返回Total，否则常为-1 - IgnoreZero: 是否忽略折后价为 0 的数据，
0不忽略、1忽略 - Product: 产品筛选条件。可选的产品 Code 请参考
references/product-code.md
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.
- references/billing-api-notes.md 26 KB
- references/install.md 3.5 KB
- references/product-code.md 2.2 KB
- scripts/common.py 6.4 KB runs code
- scripts/list_amortized_cost_bill_detail.py 4.2 KB runs code
- scripts/list_bill_detail.py 4.1 KB runs code
- scripts/list_bill_overview_by_category.py 2.0 KB runs code
- scripts/list_bill_overview_by_prod.py 3.1 KB runs code
- scripts/list_split_bill_detail.py 4.4 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.
- 4d ago First seen · 458 lines · 82 tokens per session scan A 3652222fdd04
byted-volcengine-finops is a skill published in the GitHub repository bytedance/agentkit-samples (449 stars, last pushed 3d ago), licensed Apache-2.0. It adds 82 tokens to every session and 4,120 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
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
check-model
Financial model audit: structural checks, formula validation, integrity testing.
equity-risk-reviewer
Use for portfolio-facing stock risk briefs that separate market facts, interpretation, and non-investment-advice boundaries.
technical-analysis
Technical analysis of US stocks using charts and indicators.
stock-valuation
Multi-method stock valuation using DCF, comparable company analysis, EV multiples, and residual income models.
chart-master
Generate professional financial charts in Mermaid, ASCII, or HTML/Chart.js — MA lines, histograms, candlestick, volume, RSI/MACD, and more for markdown reports.