install-openclaw

install-openclaw is a skill for Claude Code, Codex from alibaba/anolisa. It costs 85 tokens per session (1,968 once invoked), scanned A, original, Apache-2.0.

A setup tool for installing and configuring OpenClaw, a local AI agent, with Alibaba Cloud Model Studio. It can also configure selected billing plans and optionally connect DingTalk.

In plain words
What is it for?
Use it to install OpenClaw, set Alibaba Cloud API credentials and model settings, choose pay-as-you-go, Coding Plan, or Token Plan billing, and verify a working local agent.
Why use it?
It removes the need to install dependencies, enter configuration manually, and check whether the local OpenClaw gateway works. It also helps avoid using the wrong API endpoint or billing setting.

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/alibaba/anolisa/install-openclaw
Any agent
npx skills add alibaba/anolisa --skill install-openclaw
Clone the repo
git clone --depth 1 https://github.com/alibaba/anolisa

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 install-openclaw

README.md
[![agentmods](https://agentmods.dev/badge/skills/alibaba/anolisa/install-openclaw.svg)](https://agentmods.dev/skills/alibaba/anolisa/install-openclaw)
Your own site
<a href="https://agentmods.dev/skills/alibaba/anolisa/install-openclaw"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/install-openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00085 $0.01968
Opus 5 $0.00043 $0.00984
Sonnet 5 $0.00017 $0.00394
Haiku 4.5 $0.00009 $0.00197

Measured 4d ago against content hash c4539064d00e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

install-openclaw 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/install_openclaw.py, scripts/install-openclaw.sh), 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.

src/os-skills/ai/install-openclaw/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw Non-Interactive Setup

Use this skill to turn a user's one-sentence request into a complete local OpenClaw setup. The normal path is one script command: resolve the Alibaba Cloud Model Studio plan, validate the API key/Base URL/model combination with the official anthropic-messages endpoint shape, install Node.js/npm/OpenClaw when needed, write config, install/restart the local gateway service, and verify a real local openclaw agent message through Gateway.

Do not execute openclaw onboard unless the user explicitly asks for interactive setup or asks to skip first-run BOOTSTRAP onboarding. After setup, always tell the user they can run openclaw onboard --skip-bootstrap if they want the first real task to run without the introductory BOOTSTRAP flow. Do not configure DingTalk unless the user provides DingTalk credentials or asks for DingTalk access.

Billing

Map user wording to --billing:

User says Use
按量付费, 后付费, DashScope, 百炼 API Key payg
Coding Plan, 订阅 coding, Coding Plan 专属 API Key coding
Token Plan, 团队版, token 订阅 token

Do not infer Coding Plan or Token Plan only from a raw API key string. A normal Alibaba Cloud Model Studio/DashScope/百炼 API Key is pay-as-you-go unless the user explicitly says Coding Plan or Token Plan.

Default to --billing payg --region china when the user does not specify billing or region. If the user gives no API key and no usable environment variable, ask for the key and include the matching source URL:

Use --region singapore only for pay-as-you-go Singapore. If the user gives a custom Alibaba Cloud compatible endpoint, pass it through with --base-url; otherwise use the billing-specific defaults from the official OpenClaw guide. For deeper billing details, read references/aliyun-model-studio-openclaw.md.

Read the full file on GitHub · 159 lines

Files

What ships with it

5 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. 4d ago First seen · 159 lines · 85 tokens per session scan A c4539064d00e

Subscribe to this mod's changes

install-openclaw is a skill published in the GitHub repository alibaba/anolisa (618 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,968 once invoked, about $0.0004 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.

Related

Other skills, from other repositories