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 Peiiii/nextclaw --skill proxy-local-ai-subscriptionsgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/proxy-local-ai-subscriptions)<a href="https://agentmods.dev/skills/peiiii/nextclaw/proxy-local-ai-subscriptions"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/proxy-local-ai-subscriptions/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/peiiii/nextclaw/proxy-local-ai-subscriptions"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/proxy-local-ai-subscriptions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 54 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 87 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 107 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Rogue Agent · line 162 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 189 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 189 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00126 | $0.03108 |
| Opus 5.5 | $0.00050 | $0.01243 |
| Sonnet 5.5 | $0.00025 | $0.00622 |
| Haiku 4.5 | $0.00013 | $0.00311 |
Grade B, and why
proxy-local-ai-subscriptions scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo -u <service-user> -H node scripts/cliproxy.mjs write-config \ How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proxy Local AI Subscriptions
把本机订阅接成受保护的 OpenAI 兼容端点，并在用户明确同意后接入 NextClaw。代理运行时固定使用 router-for-me/CLIProxyAPI；本 skill 只负责接入、校验和故障诊断，不复制代理实现。
安全边界
- 只绑定
127.0.0.1，不支持公网、局域网、容器跨主机或反向隧道暴露。 - 只供当前用户本人使用。若用户要求共享账号、转售、规避订阅限制或绕过配额，停止并建议使用官方 API。
- OAuth token 只保存在 CLIProxyAPI 的 auth 目录；NextClaw 只保存代理生成的本地 API key。
- 不在命令行参数、聊天回复或日志里展示 API key。所有 bundled scripts 通过 mode
0600的 key 文件交换密钥。 - 当前审计与真实验收基线是 CLIProxyAPI
v7.2.90。check只自动接受7.2.x；其他版本必须重新审计官方配置和登录合同后，才可用--allow-unaudited-version继续。 - Marketplace 安装只复制 skill 文件，不代表代理已经安装或登录。必须完成下面的真实验证后才能宣告可用。
- CLIProxyAPI 必须由 macOS Homebrew services 或 Linux systemd 独立托管。
nohup、shell 后台&、NextClaw 工具进程或一次端口可达都只能用于诊断，不能作为完成状态。
工作流
1. 先做只读检查
确认操作系统、cliproxyapi、nextclaw 和当前服务状态。不要先改配置或重启服务。
macOS 首选官方 Homebrew formula：
brew info cliproxyapi --json=v2
若缺失，说明将安装第三方 MIT 工具及其用途，得到用户同意后执行：
brew install cliproxyapi
Linux 必须使用 CLIProxyAPI 官方发布物或官方安装说明，并把真实二进制路径显式传给 bundled scripts；服务必须使用第 4 步生成的独立 systemd unit。Windows 尚无持久服务合同，不得在 Windows 上继续到 provider 写入或宣告完成。
2. 生成 localhost-only 配置
从本 skill 目录运行：
node scripts/cliproxy.mjs write-config \
--config "$(brew --prefix)/etc/cliproxyapi.conf" \
--auth-dir "$HOME/.cli-proxy-api" \
--api-key-file "$HOME/.cli-proxy-api/nextclaw-api-key"
Linux 把配置、API key 与 OAuth auth 目录放在将要运行服务的普通用户 home 内，并以该用户执行配置生成；不要让 root 创建 mode 0600 文件后再让普通用户服务读取。例如：
sudo -u <service-user> -H node scripts/cliproxy.mjs write-config \
--config <service-home>/.cli-proxy-api/cliproxyapi.conf \
--auth-dir <service-home>/.cli-proxy-api \
--api-key-file <service-home>/.cli-proxy-api/nextclaw-api-key
<service-user> 与 <service-home> 必须来自机器上的真实账户信息，不得猜测；配置、OAuth 和 systemd unit 始终复用这一组值。
脚本会生成本地 API key、把 key 与配置设为 0600、关闭管理 API/控制面板，并把 factory template 自动备份后替换。若配置属于用户已有环境，脚本会拒绝覆盖；先解释差异并取得明确同意，才可加 --force。不要手写 YAML，也不要绕过备份保护。
若已存在运行中的 CLIProxyAPI，修改或重启前先告知会短暂中断该代理。不要擅自复用另一个实例的端口、auth 目录或 API key。
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.
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.
- 1mo ago First seen · 221 lines · 126 tokens per session scan B 2571773fa4fe
proxy-local-ai-subscriptions is a skill published in the GitHub repository Peiiii/nextclaw (262 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 3,108 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
deepseek-helper
A guide for using the DeepSeek API, a service that lets programs send requests to DeepSeek language models. It covers model choice, example requests, prompt improvements, cost estimates, and common API errors.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
ai-prompt-crafter
Advanced prompting techniques for any AI model covering system prompts, chain-of-thought reasoning, few-shot examples, structured output formats, context management, multi-turn conversation strategies, and a reusable prompt template library. Use when the user asks about ai prompt crafter, related techniques, best…
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…
prompt-engineering
Craft effective prompts that get the best results from language models.
azure-openai-patterns
Azure OpenAI API patterns for rate limiting, function calling, error handling, and token optimization.