agentmods.dev

arkcli-custommodel

arkcli-custommodel is a skill for Claude Code, Codex from volcengine/ark-cli. It costs 137 tokens per session (4,299 once invoked), scanned A, original, Apache-2.0.

A manager for custom AI models: model files that you trained or fine-tuned yourself. It can import them, show their status and details, change descriptions, remove them, or prepare them for deployment.

In plain words
What is it for?
Use it to upload model weights from veTOS, inspect your custom models, update their information, delete unused models, or quantize a ready model before deployment.
Why use it?
It keeps custom model files and their use in online endpoints in one place, while making potentially costly changes explicit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is → +deploy --model cm-xxxxx ... （若已有 Running Endpoint 会复用；详见 ../arkcli-deploy/SKILL.md）.

not rated 143repo +1 changed 17d ago A scan SkillSpector: pass 137 tokens original Apache-2.0

Good fit Use it to upload model weights from veTOS, inspect your custom models, update their information, delete unused models, or quantize a ready model before deployment.

Compare 6 skills from other repositories ↓
View source ↗ volcengine/ark-cli
Install

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.

Clone the repo
git clone --depth 1 https://github.com/volcengine/ark-cli
agentmods
npx agentmods add skills/volcengine/ark-cli/arkcli-custommodel

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for arkcli-custommodel

README.md
[![agentmods](https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-custommodel/github.svg)](https://agentmods.dev/skills/volcengine/ark-cli/arkcli-custommodel)
Your own site
<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-custommodel"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-custommodel/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.

agentmods 80×15 button for arkcli-custommodel

Your own site · 80×15
<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-custommodel"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-custommodel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,299 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00137 $0.04299
Opus 5.5 $0.00055 $0.01720
Sonnet 5.5 $0.00027 $0.00860
Haiku 4.5 $0.00014 $0.00430

Measured 17d ago against content hash bc6fa8b20600, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

skills/arkcli-custommodel/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 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 Action UploadModel;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 skill upload 命令,走 UploadModel API)
    • 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 Action CreateCustomModel,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

Read the full file on GitHub · 178 lines

Files

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.

Changes

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.

  1. 17d ago Changed bc6fa8b20600
  2. 1mo ago Changed · +14 lines 724c65d43bf2
  3. 1mo ago First seen · 164 lines · 137 tokens per session scan A ec6170fa26f6

Subscribe to this mod's changes

arkcli-custommodel is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 137 tokens to every session and 4,299 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.

Data and AILLMai-agentai-skillsarkclidoubao
Related

Other skills, from other repositories

system-prompts

Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.

can1357/oh-my-pi · 40 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

pyhealth

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…

synthetic-sciences/openscience · 109 tokens

deepchem

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…

synthetic-sciences/openscience · 78 tokens

shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…

synthetic-sciences/openscience · 109 tokens

torch-geometric

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

synthetic-sciences/openscience · 41 tokens