Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/volcengine/ark-clinpx agentmods add skills/volcengine/ark-cli/arkcli-usageWrote 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-usage)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-usage"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-usage/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-usage"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-usage.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 | $0.00266 | $0.04702 |
| Opus 5.5 | $0.00106 | $0.01881 |
| Sonnet 5.5 | $0.00053 | $0.00940 |
| Haiku 4.5 | $0.00027 | $0.00470 |
Grade A, and why
arkcli-usage 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli usage
CRITICAL — 开始前 MUST 先用 Read 工具读取 ../arkcli-shared/SKILL.md,其中包含认证闸门、配置排查与共享安全规则
CRITICAL — usage stats 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-stats.md,禁止直接盲目调用命令。
CRITICAL — usage plan 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-plan.md,禁止直接盲目调用命令。
CRITICAL — usage plan-details 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-plan-details.md,禁止直接盲目调用命令。
CRITICAL — Coding Plan / Coding Plan Team 当前不提供按模型套餐明细。这类问题只能用 usage plan --product coding-plan（团队版用 --product coding-plan-team）给 quota 快照并明说能力边界；禁止改跑 usage stats 后把 platform / Endpoint Token 统计冒充 Coding Plan 套餐按模型明细。
CRITICAL — 上述 Coding Plan 问题在本轮执行 usage plan 并说明边界后就停止。不主动追加 Endpoint / platform usage stats，因为它无法归因为 Coding Plan 套餐明细；只有用户在知道两者不同后另行明确要求「再看 platform / Endpoint 用量」，才开新查询。
CRITICAL — usage balance 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-balance.md,禁止直接盲目调用命令。
CRITICAL — usage seats 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-seats.md,禁止直接盲目调用命令。
数据时效(务必先看):
usage stats走的是上游 BFF 的聚合管道,数据有 5–30 分钟延迟,定位为「日级 / 聚合分析」。 不要把它用于实时预算监控、限流、实时告警等需要秒级精度的控制场景——这类场景请直接读+chat/+gen等推理命令返回里的.usage字段(per-request、零延迟,详见 arkcli-chat 与 arkcli-gen)。
语音模型边界：TTS / ASR / 配音 / 朗读 / 播客 / 音色 / 实时语音交互，或
doubao-seed-tts-*/doubao-seed-asr-*/seedasr-*等广场语音模型，当前在 arkcli 只支持models search发现。不要用usage stats --model、usage plan-details或套餐/余额命令回答语音模型用量；直接说明 arkcli 不支持查询语音模型费用或用量。
stats / plan / plan-details / balance 区分:
stats出"按 token 计费的 inference 用量"(任何身份,5–30 分钟延迟)plan出"订阅套餐的 quota 快照"(AgentPlan / CodingPlan 个人版 + 团队版的"我用了几成 / 几号刷新")plan-details出"AgentPlan 按模型 / 套餐内外的时间序列调用明细"(AgentPlan 个人版 + 团队版,CodingPlan 没有按模型 endpoint)balance出"还剩多少 X"(余额视角,--type free-quota / media-asset / plan三选一)seats出"团队席位用量 admin 视角"(每个 seat 用了多少 / 套餐百分比;只是用量视图)。席位的列表 / 绑定 / 分配 / API Key 轮换 走arkcli-plans的plans team seat-list / seat-assign / rotate-apikey。用户问「我的套餐还剩多少额度」→
plan或balance --type plan(后者输出更精简);「我哪个模型用得最多」→ Agent Plan 用plan-details，Coding Plan 只能用plan给 quota 快照并说明不支持按模型拆分;「我今天用了多少 token」→stats;「我还剩多少免费额度 / 媒资库容量」→balance;「每个 seat 用了多少 / 团队席位用量分布」→seats --with-usage(纯管理类:谁绑了哪个 seat / 列出席位 / 分配席位 / 轮换 key →arkcli-plans)。
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.
- 17d ago Changed · -4 lines 65c94521c9dc
- 1mo ago Changed 20660f200a14
- 1mo ago Changed · +3 lines · +24 tokens per session dfb174e4fbbf
- 1mo ago First seen · 147 lines · 242 tokens per session scan A b065a3afc79e
arkcli-usage is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 266 tokens to every session and 4,702 once invoked, about $0.0011 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
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
batch-file-ops
Batch-Dateioperationen (Löschen, Verschieben, Kopieren, Auflisten) mit Glob-Mustern. CLI-Werkzeug für effiziente Dateisystem-Operationen. Ohne Abhängigkeiten.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…