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/volcengine/ark-cli/arkcli-custommodelnpx skills add volcengine/ark-cli --skill arkcli-custommodelgit clone --depth 1 https://github.com/volcengine/ark-cliWhat 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 | $0.00137 | $0.03741 |
| Opus 5 | $0.00068 | $0.01870 |
| Sonnet 5 | $0.00027 | $0.00748 |
| Haiku 4.5 | $0.00014 | $0.00374 |
Grade A, and why
arkcli-custommodel 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 2d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli models custommodel
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 — 所有 models custommodel 命令在执行之前，务必先用 Read 工具读取其对应的 reference 文档，禁止直接盲目调用命令。
CRITICAL — 写操作（upload / update / delete / quantize）必须先确认用户意图。删除前必须确认是否还有 endpoint 引用。
守卫与使用原则
- 自定义模型相关需求优先使用
arkcli models custommodel ... - 这些命令虽然是标准 CLI 类型，但实现入口仍然来自
shortcuts/models/ - 只有产品命令无法覆盖时，才回退到
../arkcli-api-explorer/SKILL.md - 本 skill 不是基础模型查询入口；基础模型目录查询转
../arkcli-models/SKILL.md - 写操作和异步任务必须把影响范围、轮询方式和后续动作串起来，不要停在单条命令
适用场景
- 把训练好/微调好的权重从 veTOS 导入到 ARK 自定义模型
- 查询账号下已有的自定义模型（"我的自定义模型有哪些 / 状态如何"）
- 查看自定义模型详情、产物形态、活跃 endpoint 引用
- 修改自定义模型展示名或描述
- 删除不再使用的自定义模型
- 把已
ready的自定义模型量化，准备给+deploy当目标
反唤起信号
- 找官方基础模型 → 用
../arkcli-models/SKILL.md的search/list/get - 直接调用自定义模型推理 → 必须先
+deploy，再走+chat/+gen - 触发模型微调任务（customization job 本身）→ 转
../arkcli-train-finetune/SKILL.md - 从精调任务的 step（
global_step_N）注册成cm-(=「导出训练产物」)→ 转../arkcli-train-finetune/SKILL.md的arkcli train finetune artifacts list / export，不要用本 skill 的upload(那是给"用户自己的 TOS 文件"用的,后端 ActionUploadModel;mcj 输出走CreateCustomModel,完全不同的 API) - 已经拿到 endpoint-id 后想管理 endpoint → 转
../arkcli-infer-endpoint/SKILL.md
cm-* 直接推理边界
- 用户要求“用
cm-*直接对话/推理/试效果”时也必须加载本 skill。明确说明cm-*是自定义模型资源 ID，不能直接传给+chat/+gen；推理前需要单独获得或部署 Endpoint。 - 该请求本身不授权部署、查询账号下 Endpoint 或发起推理。未经用户继续授权，不执行
arkcli +deploy、arkcli +chat、arkcli infer endpoint list，也不拼接jq等扫描方案。 - 只说明边界和下一步选择；用户明确要求继续部署后，才转
../arkcli-deploy/SKILL.md并遵守其确认流程。
核心概念
- 本 skill 统一把
arkcli models custommodel ...管理的资源称为自定义模型（CustomModel，ID 形如cm-xxxxx）；它与../arkcli-models/SKILL.md中search/list/get操作的官方基础模型（FoundationModel）是两套独立资源 - 自定义模型来源有两类：
import—— 用户从 TOS 上传权重导入(本 skillupload命令,走UploadModelAPI)customization—— 通过模型微调任务产出(走../arkcli-train-finetune/SKILL.md的train finetune artifacts export,底层是另一个 OpenAPI ActionCreateCustomModel,跟upload不互通)
- 生命周期状态机：
preparation → processing → ready（成功）或failed；导出场景另有exporting/exportfailed - 量化是单独流程：先
available-quantizations <id>查可用模式，并查看supported_inference_types_by_quantization预判每种量化方式支持的部署/付费形态；再quantize <id> --quantization <mode>提交量化任务，结果是一个独立的新 cm-xxxxx。源模型、量化结果模型、最终部署出来的 endpoint 是三类不同资源，不能混用 ID - 自定义模型 ID（
cm-xxxxx）不是<name>-<primary_version>形式，不能直接作为+chat/+gen的--model；必须先通过arkcli +deploy获得 endpoint，拿ep-xxx才能调用推理。若该自定义模型已有 Running Endpoint，+deploy会直接复用已有 endpoint
What ships with it
8 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/arkcli-custommodel-available-quantizations.md 1.1 KB
- references/arkcli-custommodel-delete.md 1.3 KB
- references/arkcli-custommodel-get.md 1.8 KB
- references/arkcli-custommodel-list.md 2.7 KB
- references/arkcli-custommodel-quantize.md 2.6 KB
- references/arkcli-custommodel-update.md 1.3 KB
- references/arkcli-custommodel-upload.md 2.7 KB
- references/evals.md 4.4 KB
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.
- 2d ago First seen · 164 lines · 137 tokens per session scan A ec6170fa26f6
arkcli-custommodel is a skill published in the GitHub repository volcengine/ark-cli (112 stars, last pushed 5d ago), licensed Apache-2.0. It adds 137 tokens to every session and 3,741 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
jobs-to-be-done
Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
scienceworld-growth-focuser
Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…