← 返回 Skills 市场

Agnic AI Gateway

Name: Agnic AI Gateway
Author: agnicpay-prog

作者 Agnic.AI · GitHub ↗ · v2.0.2 · MIT-0

cross-platform ⚠ suspicious

118

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ai-gateway

功能描述

Access 340+ AI models via the Agnic AI Gateway -- chat, image generation, model listing. Use when the user wants to chat with AI, generate images, ask GPT, u...

使用说明 (SKILL.md)

AI Gateway

Access 340+ AI models (OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more) through the Agnic AI Gateway. Costs are deducted from your USDC balance per token. Free models available for development.

Authentication

Run npx agnic@latest status --json to verify. If not authenticated:

Headless (CI/server/agent): Set AGNIC_TOKEN env var or pass --token \x3Ctoken>
Interactive (has browser): Run npx agnic@latest auth login

See the authenticate-wallet skill for details.

Commands

List models

npx agnic@latest ai models [--provider \x3Cname>] [--search \x3Cterm>] [--json]

Chat with a model

npx agnic@latest ai chat --model \x3Cprovider/model-name> --prompt "\x3Ctext>" [--system "\x3Ctext>"] [--json]

Generate an image

npx agnic@latest ai image --prompt "\x3Ctext>" [--aspect-ratio 16:9] [--output file.png] [--json]

Models use provider/model-name format (e.g., openai/gpt-4o, meta-llama/llama-3.3-70b). See reference/models-and-options.md for full model list, all options, and input validation rules.

Examples

# List OpenAI models
npx agnic@latest ai models --provider openai --json

# Chat with GPT-4o
npx agnic@latest ai chat --model openai/gpt-4o --prompt 'Explain quantum computing in one sentence'

# Use a free model
npx agnic@latest ai chat --model meta-llama/llama-3.3-70b --prompt 'What is 2+2?' --json

# Generate an image
npx agnic@latest ai image --prompt 'A sunset over mountains' --output sunset.png

# Generate widescreen image
npx agnic@latest ai image --prompt 'Cyberpunk cityscape' --aspect-ratio 16:9 --output city.png

Prerequisites

Must be authenticated (npx agnic@latest status to check)
Wallet must have USDC balance (free models available for testing)

Error Handling

Common errors:

"Not authenticated" -- Run npx agnic@latest auth login or set AGNIC_TOKEN
"Insufficient balance" -- Fund wallet at app.agnic.ai
"Model not found" -- Check available models with npx agnic@latest ai models
"No image returned" -- Try a different model or rephrase the prompt
"Rate limit exceeded" -- Wait a moment and retry

安全使用建议

This skill appears to be a thin wrapper around the Agnic CLI and is coherent with its stated purpose, but proceed with caution. Key things to consider before installing or running it in a sensitive environment: - Metadata/manifest mismatch: SKILL.md says you may need AGNIC_TOKEN, but the registry metadata does not declare it. Treat AGNIC_TOKEN as a sensitive credential and avoid placing it in a shared/global environment until you verify scope. - npx@latest risk: The skill runs npx agnic@latest which will fetch and execute code from npm at runtime. Prefer a pinned, audited version or inspect the package source (repo/homepage) before using. Running unpinned npx commands can execute arbitrary code if the package is compromised. - Unknown source: There is no homepage or repo listed. Verify the npm package owner, repository, and package contents (or run in an isolated/ephemeral environment) before giving it credentials or payment funds. - Payment implications: The gateway charges USDC from a wallet. Use a dedicated test wallet with limited funds for initial trials and confirm billing behavior on app.agnic.ai. - Safer alternatives: If you must use this during automation, pin the CLI version (npx [email protected]) or vendor the CLI binary after manual review; avoid long-lived token exposure; consider running commands in a sandbox/container. If you want, I can: (a) show how to inspect the agnic npm package before running it, (b) draft a minimal wrapper that pins a specific version, or (c) produce guidance for creating a temporary wallet and limited-scope token for testing.

功能分析

Type: OpenClaw Skill Name: ai-gateway Version: 2.0.2 The skill provides a legitimate interface to the Agnic AI Gateway via the 'agnic' CLI tool. It includes proactive security instructions in 'reference/models-and-options.md' that direct the AI agent to perform input validation and shell-escaping to prevent command injection. No indicators of data exfiltration, malicious persistence, or harmful prompt injection were found.

能力标签

cryptorequires-walletrequires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The skill description (access Agnic Gateway to list/chat/generate images across many models) matches the commands shown (npx agnic ai ...). Requiring an Agnic auth token and a USDC-backed wallet is coherent with the payment model. However, the package source is unknown (no homepage) and the metadata declares no required env vars even though SKILL.md instructs use of AGNIC_TOKEN — a documentation/metadata mismatch.

ℹ Instruction Scope

SKILL.md instructs the agent to run npx agnic@latest commands (status, auth, ai chat/image/models) and gives input-validation guidance (good). It also tells the agent how to authenticate (AGNIC_TOKEN or interactive login). The instructions do not attempt to read unrelated system files, but they do rely on executing external code fetched at runtime via npx, which can run arbitrary code and is therefore a scope/risk consideration.

⚠ Install Mechanism

There is no install spec in the registry, but runtime usage relies on npx agnic@latest which downloads and executes the latest package from npm each run. Dynamic installs from npm (unversioned @latest) are higher risk because package content can change and execute arbitrary code; the skill does not recommend or pin a specific, audited version or provide a repository/homepage to verify.

⚠ Credentials

SKILL.md expects AGNIC_TOKEN for headless auth and mentions a USDC-backed wallet (payment). The registry metadata lists no required env vars or primary credential — this mismatch reduces transparency. Requesting an auth token and wallet access is proportionate to the stated functionality, but the skill should declare AGNIC_TOKEN (and describe its scope) in metadata. Storing/using payment credentials or long-lived tokens in shared agent environments has obvious sensitivity.

✓ Persistence & Privilege

The skill is not always-enabled and does not request elevated persistence. disable-model-invocation is false (normal). There is no indication it modifies other skills or system-wide configs.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ai-gateway
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-gateway 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v2.0.2

v2.0.2 — Synced with upstream agnic-wallet-skills: - Added context: fork for execution isolation - Added reference/models-and-options.md for progressive disclosure - Standardized authentication (browser OAuth + headless AGNIC_TOKEN) - Tightened descriptions for AI agent discovery

v1.0.0

Initial publish of AI Gateway for Agnic wallet agent.

元数据

Slug ai-gateway

版本 2.0.2

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题

Agnic AI Gateway 是什么？

Access 340+ AI models via the Agnic AI Gateway -- chat, image generation, model listing. Use when the user wants to chat with AI, generate images, ask GPT, u... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 118 次。

如何安装 Agnic AI Gateway？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-gateway」即可一键安装，无需额外配置。

Agnic AI Gateway 是免费的吗？

是的，Agnic AI Gateway 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Agnic AI Gateway 支持哪些平台？

Agnic AI Gateway 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Agnic AI Gateway？

由 Agnic.AI（@agnicpay-prog）开发并维护，当前版本 v2.0.2。