byted-vms-aicall

byted-vms-aicall is a skill for Claude Code, Codex from bytedance/agentkit-samples. It costs 68 tokens per session (1,232 once invoked), scanned A, original, Apache-2.0.

A tool for creating and checking AI-powered outbound phone tasks. The AI follows a selected script to call people for purposes such as bookings, reminders, surveys, or follow-ups.

In plain words
What is it for?
Create calls for restaurant bookings, payment reminders, customer follow-ups, or satisfaction surveys, and query task progress.
Why use it?
It turns a phone task into a managed workflow: choose a script, provide numbers and details, then check the results.

Skill for Claude CodeCodex ✓ vendor

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Create calls for restaurant bookings, payment reminders, customer follow-ups, or satisfaction surveys, and query task progress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bytedance/agentkit-samples/byted-vms-aicall
About the project

bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.

bytedance/agentkit-samples · 450 stars · on GitHub

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.

Any agent
npx skills add bytedance/agentkit-samples --skill byted-vms-aicall
Clone the repo
git clone --depth 1 https://github.com/bytedance/agentkit-samples

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 byted-vms-aicall

README.md
[![agentmods](https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-vms-aicall/github.svg)](https://agentmods.dev/skills/bytedance/agentkit-samples/byted-vms-aicall)
Your own site
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-vms-aicall"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-vms-aicall/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 byted-vms-aicall

Your own site · 80×15
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-vms-aicall"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-vms-aicall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,232 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 $0.00068 $0.01232
Opus 5 $0.00034 $0.00616
Sonnet 5 $0.00014 $0.00246
Haiku 4.5 $0.00007 $0.00123

Measured 6d ago against content hash c59cbd41184f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

byted-vms-aicall 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/_topclient.py, scripts/aicall.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/byted-vms-aicall/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

byted-vms-aicall · 火山云通信智能外呼

何时使用

当用户希望 AI 机器人代为外呼办事时:

  • 「帮我打给 1XXXXXXXXXX 预订餐厅, 餐厅 xx, 时间 xx, 几人 xx」
  • 「让机器人催一下这批欠费用户」
  • 「帮我做一次满意度回访」
  • 「查一下昨天那批外呼任务的结果」

环境变量

按以下优先级解析鉴权 (与其他 vms-* skill 一致):

  1. ARK_SKILL_API_KEY + ARK_SKILL_API_BASE → 火山引擎 arkclaw 企业版. 请先在火山后台页面配置好 AK/SK, 由 arkclaw 注入这两个环境变量 (ARK_SKILL_API_KEY 为 API 密钥, ARK_SKILL_API_BASE 为 API 基础地址), 脚本以 Bearer 鉴权直连该网关, 无需本地签名;
  2. VOLC_ACCESS_KEY + VOLC_SECRET_KEY (兼容 VOLCENGINE_ACCESS_KEY/VOLCENGINE_SECRET_KEY) → 个人版 arkclaw / openclaw / coco / aime / claudecode 等普通 agent, 用户直接把 AK/SK 告诉 agent, 脚本本地做 HMAC-SHA256 (Volc V4) 签名;
  3. 否则报错并提示用户填入 AK/SK.

命令

# 1. 查询可用话术 (GET, 无参或可选 --scene)
python3 scripts/aicall.py list_scripts [--scene restaurant_booking]

# 2. 创建外呼任务 (POST, PhoneList 是对象数组, 由脚本根据 --phone-list + --variable-values 构造)
python3 scripts/aicall.py create_task \
    --script-id <ScriptId> \
    --phone-list "<PhoneA>,<PhoneB>" \
    --variable-values '{"餐厅":"必胜客","时间":"2026-05-29 18:00","人数":"3","备注":"靠窗"}'

# 3. 查询任务进度 / 通话结果 (GET)
python3 scripts/aicall.py query_task --task-id <TaskId>

标准执行流程

  1. 从用户语义里抽取「目标号码 + 任务意图 + 关键变量」.
  2. list_scripts 找匹配话术. 如果无, 给出已有话术列表让用户选, 或提示去控制台创建话术: https://console.volcengine.com/cloud_vms/aicall .
  3. 直接调用 create_task 创建任务, 返回 TaskId. 无需选号码池: 平台按话术绑定的默认号码池自动选号.
  4. 用户后续问进度时, 用 query_task 拉结果, 返回任务进度、通话明细 (含 ASR、意图标签、通话时长等).

错误兜底

  • RESOURCE_NOT_FOUND (话术不存在) → 返回当前可用话术列表.
  • 鉴权失败 → 提示检查 AK/SK. 普通 agent (个人版 arkclaw / openclaw / coco / aime / claudecode) 检查 VOLC_ACCESS_KEY/VOLC_SECRET_KEY; 火山引擎 arkclaw 企业版需先在火山后台页面配置好 AK/SK, 再确认 ARK_SKILL_API_KEY/ARK_SKILL_API_BASE 已注入.

参考

📚 基础知识 / 参数传递参考

调用任何 action 前 (尤其是 create_taskPhoneList / VariableValues 字段构造), 请先阅读本 skill 内置的本地基础知识文档:

references/vms-fundamentals.md

该文档覆盖 SubServiceType 枚举 / 号码状态映射 / CallId 格式 / 录音 CDN / 出口 IP 白名单等通用规范, 所有 vms-* skill 共用同一份内容. 本地文件在外网受限 环境也能用, 性能优于远程拉取. 若需对照原始版本, 可回看飞书原文: https://bytedance.sg.larkoffice.com/docx/Mv32dc0yooBn7txDxW8lsDdDgYb

Read the full file on GitHub · 90 lines

Files

What ships with it

4 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. 6d ago First seen · 90 lines · 68 tokens per session scan A c59cbd41184f

Subscribe to this mod's changes

byted-vms-aicall is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 5d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,232 once invoked, about $0.0003 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 2026-09-03.