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 skills add volcengine/ark-cli --skill arkcli-infer-endpointgit clone --depth 1 https://github.com/volcengine/ark-cliWrote 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-infer-endpoint)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-infer-endpoint"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-infer-endpoint/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-infer-endpoint"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-infer-endpoint.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 | $0.00258 | $0.03296 |
| Opus 5.5 | $0.00103 | $0.01318 |
| Sonnet 5.5 | $0.00052 | $0.00659 |
| Haiku 4.5 | $0.00026 | $0.00330 |
Grade A, and why
arkcli-infer-endpoint 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli infer endpoint
CRITICAL — 显式脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是本 skill 的正向触发，不得因为出现“创建 Endpoint”就转到 arkcli-deploy。
CRITICAL — 模型候选复用本轮完整结果；截断、空结果的有界恢复统一复用 Deploy 规则。认证/权限失败不重试、不切身份、不修改配置或把凭证写进命令行；其他失败保留原始错误，不盲换命令。
CRITICAL — 开始前 MUST 先读取 ../arkcli-shared/SKILL.md。
使用原则
- 推理接入点相关需求优先使用
arkcli infer endpoint ... - 这些命令虽然是标准 CLI 类型，但实现入口仍然来自
shortcuts/inferendpoint/ - 只有产品命令无法覆盖时，才回退到
../arkcli-api-explorer/SKILL.md infer endpoint create成功后会返回 EndpointId- 这个
Id应作为后续get / start / stop的输入，也可以传给../arkcli-code-example/SKILL.md生成带真实endpoint-id的调用示例 - 如果已经通过
infer endpoint create拿到Id，不要再调用+deploy试图"二次部署"；+deploy本身就是创建 Endpoint 的工作流 infer endpoint create --billing-method当前只支持token；它是可选项，显式传token时会先校验模型是否支持 token 推理方式，创建请求本身保持默认行为- 语音模型不是 Endpoint create 目标：TTS / ASR / 配音 / 播客 / 音色 / 实时语音交互，或模型名命中
doubao-seed-tts-*、doubao-seed-asr-*、seedasr-*时，不要用infer endpoint create或 Raw CRUD 绕过；只转arkcli-models说明"广场可搜，但当前 arkcli 不支持 Endpoint 创建"。
「我的接入点」语义
用户说**"我的推理接入点 / 我创建的 / 我有多少个 / 列出我的"** → 必须加 --mine --page-all：
arkcli infer endpoint list --mine --page-all --page-size 100 --format json
服务端按 sys:ark:createdBy tag 过滤，只返回当前 SSO sub-user 创建的 endpoint。
需要 SSO 子账号身份；root 账号 / AK-SK 报错不算空结果，认证处理服从当前 shared 宿主协议，不自动重登。
详细行为见 references/arkcli-infer-endpoint-list.md。
本人查询为空的三级恢复
--mine查询成功、完整且.TotalCount == 0/.Items == []才进入下一层；鉴权、权限、网络、参数错误及分页不完整均不能当空。- 向用户说明接下来查“当前用户 API Key 用过的 EP”，不冒充“本人创建”。按 usage stats 使用
arkcli usage stats --start <29天前日期> --end <今天日期> --mine --mine-by=apikey --by endpoint --format json；原请求有时间范围就保留。对完整结果里的非空ModelEndpoint去重，逐个infer endpoint get <真实ID>，保留原--status/--model条件（get 结果本地核对）。不能给 endpoint list 发明--mine-by。历史 ID 当前 NotFound 时单列“历史调用过、当前不可见”，不称已删除；其他失败原样报告。 - 第二层也成功但没有非空历史 ID 时，询问用户是否查看账号全量；已明确授权该范围时可继续。执行
arkcli infer endpoint list --page-all --page-size 100 --format json并保留原筛选条件，结果明确标“账号全量 fallback（已取消 --mine，不能保证本人创建）”。拒绝扩大范围则交付本人查询为空，不自动全账号。
What ships with it
7 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-infer-endpoint-create.md 5.4 KB
- references/arkcli-infer-endpoint-delete.md 3.0 KB
- references/arkcli-infer-endpoint-get.md 4.6 KB
- references/arkcli-infer-endpoint-list.md 8.8 KB
- references/arkcli-infer-endpoint-start.md 1.1 KB
- references/arkcli-infer-endpoint-stop.md 1.1 KB
- references/arkcli-infer-endpoint-update.md 2.5 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.
- 17d ago Changed · +9 lines 8fff780d0916
- 1mo ago Changed · +38 lines · +42 tokens per session 59f5c5394d13
- 1mo ago First seen · 74 lines · 216 tokens per session scan A 36e88cb0c543
arkcli-infer-endpoint is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 258 tokens to every session and 3,296 once invoked, about $0.0010 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
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
knowledge-model-and-provider-runtime
A codebase guide for choosing AI models and providers, sending requests, recovering from failures, and recording runtime information.
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Gemini", "expose tools to Gemini", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
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…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…