arkcli-helper

A local setup tool for configuring AI-agent clients such as Claude Code, Codex, OpenCode, OpenClaw, and Hermes. It can connect them to Ark plans or platform endpoints and add selected MCP tools, which are external capabilities an agent can call.

In plain words
What is it for?
It helps configure model access and add MCP capabilities such as professional datasets, web search, agent memory, or cloud-computer access.
Why use it?
It removes the need to manually edit each client’s provider, model, and tool configuration.

Skill for Claude CodeCodex

Install

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.

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

Made for: Claude Code, Codex.

Per session 345 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,418 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00345 $0.08418
Opus 5 $0.00172 $0.04209
Sonnet 5 $0.00069 $0.01684
Haiku 4.5 $0.00034 $0.00842

Measured 2d ago against content hash b91fc970a969, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

arkcli-helper scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `codex` 支持 model/provider + MCP。默认 **profile 模式**写 `~/.codex/arkcli.config.toml`,需用 `codex --profile arkcli` 启动 terminal/TUI 才生效;传 `--codex-config-scope global` 才写 `~/.codex/config.toml`,该范围可能被 Codex CLI/TUI、Codex App、
skills/arkcli-helper/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

arkcli helper —— 给本机 AI Agent 配置 Plan / Platform Endpoint / 注入 MCP

前置: 先用 Read 读 ../arkcli-shared/SKILL.md 获取共享安全规则与认证闸门。

CRITICAL — arkcli helper 整个命令域不支持 --dry-run Helper 面向 TTY/本地 harness 配置,不是 API request preview。任何 helper 命令带 --dry-run 都应 fail-fast 为 unknown flag;Agent 不得生成该 组合,也不得把它当作写操作保护。真实 configure/reset/mcp/supabase 仍必须先展示目标与路径并取得明确确认。

命令选择(先选最具体的子命令)

  • 用户要查看或配置 Agent 的 model/provider、Plan、Platform Endpoint,或核对 --with-mcp / --with-supabase / --with-routing 等非交互选项时,必须选择 arkcli helper configure;只查看用法也要运行 arkcli helper configure --help,不能退化成父级 arkcli helper --help
  • 用户只要 Harness 工具、不改 model/provider 时,选择 arkcli helper mcp [target]。不传 --capability 配整组 Agent Plan MCP;只要专业数据集、豆包搜索或 Agent 记忆时分别传 --capability datapro|web-search|agent-memory;只要云电脑时传 --capability cua。选择豆包搜索后默认关闭目标客户端的原生 WebSearch/web_search,用户要求保留时加 --keep-native-websearch。发生关闭时立即输出作用域、配置文件和完整 reset 命令。只查看用法时运行 arkcli helper mcp --help
  • arkcli-auth 只处理实际认证阻塞。用户仅要求查看 helper 的 --help 时,不要转去登录、init-volc 或其他认证命令。

适用场景 / 唤起信号

  • 用户要给本机 Claude Code / Codex / OpenCode / OpenClaw / Hermes 配置 Plan 或 Platform Endpoint 的 model/provider。
  • 用户要给支持的目标 Agent 配置豆包搜索、专业数据集或 OpenViking MCP,只安装云电脑 CUA Skill,或配置 byted-supabase。
  • 用户询问 arkcli helper 的安装态、配置态、文件落点、重载方式或 Agent Plan Harness 抵扣/超额后付费矩阵。

反唤起信号 / 不该唤起

  • 只查询/购买/续费套餐或管理团队席位时转 arkcli-plans
  • 只搜索基础模型、查询用量或价格时分别转 arkcli-modelsarkcli-usagearkcli-pricing
  • 把 arkcli 内嵌 Skills 安装到 Agent 时转 arkcli-connect;不要把“安装 arkcli skill”误判为配置 Harness。
  • 仅排查登录、401 或 profile 覆盖问题时转 arkcli-auth / arkcli-config,不要反复重写 Agent 配置。

TTY Harness 能力矩阵(Agent Plan / Agent Plan Team)

真人直接运行 arkcli helper 时,向导顺序固定为:选择 Agent Plan profile → 选择模型 → 选择 AI Agent → 写入 model/provider → 进入 Harness 能力选择页。每行同时显示:

  1. 本次是否重新配置([✓] 已选、[ ] 未选、[-] 当前不可配置);
  2. 套餐抵扣是否开启;
  3. 超额后付费是否开启;
  4. 当前所选 AI Agent 的本地配置状态。

本次选择与当前状态互相独立:默认勾选全部可配置能力;已显示“已配置”的能力进入下一步后仍必须重新执行配置。仅远端能力、当前 Agent 不支持以及团队版不提供的 Agent 记忆显示 [-],不能选择。用户可取消任意能力;全部取消后选择“进入配置”会被阻止,也可以显式选择“跳过能力配置”。

Read the full file on GitHub · 230 lines

Files

What ships with it

2 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. 2d ago First seen · 230 lines · 345 tokens per session scan B b91fc970a969

Subscribe to this mod's changes

arkcli-helper is a skill published in the GitHub repository volcengine/ark-cli (112 stars, last pushed 5d ago), licensed Apache-2.0. It adds 345 tokens to every session and 8,418 once invoked, about $0.0017 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

kangarooking/cangjie-skill · 136 tokens

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…

wondelai/skills · 211 tokens

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…

wondelai/skills · 137 tokens

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.

rorkai/app-store-connect-cli-skills · 60 tokens

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…

aklofas/kicad-happy · 119 tokens

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…

zjunlp/SkillNet · 71 tokens