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 volcengine/ark-cli --skill arkcli-billinggit clone --depth 1 https://github.com/volcengine/ark-cliWrote 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/volcengine/ark-cli/arkcli-billing)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-billing"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-billing/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/volcengine/ark-cli/arkcli-billing"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-billing.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 | $0.00128 | $0.02173 |
| Opus 5.5 | $0.00051 | $0.00869 |
| Sonnet 5.5 | $0.00026 | $0.00435 |
| Haiku 4.5 | $0.00013 | $0.00217 |
Grade A, and why
arkcli-billing 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 17d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli billing
执行前 MUST 读取 ../arkcli-shared/SKILL.md (认证 / 全局规则) 和 references/arkcli-billing-list.md (参数详解)。
适用场景
- 查询某账期月或月范围内的拆分账单明细(结算金额 / Token 用量)
- 按 Endpoint、API Key、产品编码、账单类型过滤拆账行
- 月度 / 季度 / 年度对账
- 排查"这个 EP / 这把 key 花了多少钱"
业务定位 — billing vs usage stats
| 维度 | usage stats |
billing list |
|---|---|---|
| 数据源 | ARK BFF 推理聚合 | 火山计费中心拆账 |
| 时效 | 5–30 分钟延迟 | T+1 出账 |
| 单位 | Token / 请求数 | CNY 金额 |
想看"用了多少 token"→ arkcli-usage;想看"花了多少钱"→ 本 skill。
Step 0：确认账单口径与范围
先分清“已结算金额”与“Token / 套餐额度消耗”，后者交给 Usage，不用单价乘估算 Token 冒充账单。用户只查某个 Endpoint、Key 或订阅时，仅查其明确范围；profile.type=platform 不能证明没有套餐。
身份上下文已知则复用，确需核实时按共享宿主协议使用 arkcli auth whoami --format json；托管宿主的注入协议优先。普通账单查询不调用可能同步/回写 Key 的 profile show/list/keys list，不为了补全账单切换身份。
- “我花了多少”先保留
--mine，按下面的本人资源流程查；用户要求订阅类账单时显式--product ark_subscription，并解释其账号/订阅范围，不称为个人 Endpoint 用量。 - “整个账号花了多少”才使用账号查询；Project 筛选按本次实际上下文说明，不能为补数擅自清空 Project、换 Profile 或换身份。
- 每条
billing list必带--start <YYYY-MM>，跨月加--end <YYYY-MM>。账期是月份，不是 Usage 的日级参数；T+1 及当期未出账部分必须披露。 - 返回的账单数组是
items，不是 Endpoint 列表的Items。解析失败、请求失败、截断与真实空列表分开报告。
快速决策
| 用户问 | 命令 |
|---|---|
| 我这个月 / 上个月花了多少 | arkcli billing list --start <YYYY-MM> --mine；明确要订阅账单时按 Step 0 另选产品并披露范围 |
| 整个账号花了多少 / 公司账号 / 整体 (无主语自指) | arkcli billing list --start 2026-05 (账号维度全量) |
| 这个 EP 花了多少 | arkcli billing list --start 2026-05 --endpoint ep-... |
| 这把 key 花了多少 | arkcli billing list --start 2026-05 --apikey ark-... |
| 账号下每个 EP / key 各花了多少 | --split-dim endpoint 或 --split-dim apikey |
| 按天 / 按每条结算明细 | --interval day 配 --day YYYY-MM-DD,或 --interval detail |
| 过去 N 个月对账 | --start ... --end ... (闭区间, 最多 24 个月) |
| 看 Agent Plan / Coding Plan 订阅类账单 | 显式 --product ark_subscription (默认查询不含) |
--mine fallback 流程 (跟 usage stats 对齐)
用户问"我...花了多少"时:
- 火山: 先
arkcli billing list --start <YYYY-MM> --mine(默认--mine-by=endpoint)- 有数据 → 用
partial_failures检查截断后,告诉用户金额合计 - 撞空 (
no endpoints owned by current sub-user) → 立即重试--mine --mine-by=apikey - 仍撞空 → 报告“在本次身份、范围和账期内未查到匹配账单”，核对时间、出账延迟和资源范围；不能据此宣称账号零资源或自动切身份
- ⛔ 禁止退化为不带
--mine的全量查询 — 全账号金额 ≠ "我花的",一旦丢--mine范围语义就跑偏(对齐 arkcli-usage 的同条款)
- 有数据 → 用
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.
- 17d ago Changed · -5 lines 6776f6e9ff84
- 29d ago Changed · +1 lines 6673ae3cdc2e
- 1mo ago Changed e05f0b57ab85
- 1mo ago First seen · 97 lines · 128 tokens per session scan A abb23e2f7948
arkcli-billing is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 128 tokens to every session and 2,173 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
fred-economic-data
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring…
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
financial-analysis
Financial figures done carefully: periods and fiscal calendars, units and currencies, reconciliation, magnitude sanity checks, sourced assumptions. Use for statements, budgets, pricing, and diligence numbers.
receipts-to-expenses
Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary. Use when given receipt photos and asked for an expense report.
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
steuer-assistent
Points to the standalone module steuer-assistent: a local, offline-first receipt worksheet for German employee income-related expenses (Werbungskosten) -- record, sum to the cent, private ZIP export. Use this skill when Werbungskosten receipts should be prepared in a structured way -- with a clear boundary: not tax…