Agent skill

Proxy Local AI Subscriptions

当用户希望把本机 Codex、ChatGPT Codex 或 Claude Code 订阅通过 localhost 暴露为 OpenAI 兼容端点，或希望在代理验证成功后把它添加成 NextClaw 自定义 provider 时使用。负责 CLIProxyAPI 安装检查、安全配置、OAuth 登录、Homebrew/systemd 持久托管、重启存活验收、NextClaw provider…

MITAuto-check: notesBackend & APIs

Install Proxy Local AI Subscriptions

skills CLI

$ npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Peiiii/nextclaw proxy-local-ai-subscriptions --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/proxy-local-ai-subscriptions .claude/skills/proxy-local-ai-subscriptions && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "proxy-local-ai-subscriptions" agent skill from https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions into .claude/skills/proxy-local-ai-subscriptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-local-ai-subscriptions", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Peiiii/nextclaw proxy-local-ai-subscriptions --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/proxy-local-ai-subscriptions .agents/skills/proxy-local-ai-subscriptions && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "proxy-local-ai-subscriptions" agent skill from https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions into .agents/skills/proxy-local-ai-subscriptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-local-ai-subscriptions", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Peiiii/nextclaw proxy-local-ai-subscriptions --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/proxy-local-ai-subscriptions .cursor/skills/proxy-local-ai-subscriptions && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "proxy-local-ai-subscriptions" agent skill from https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions into .cursor/skills/proxy-local-ai-subscriptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-local-ai-subscriptions", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Peiiii/nextclaw.git --path skills/proxy-local-ai-subscriptions

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Peiiii/nextclaw proxy-local-ai-subscriptions --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/proxy-local-ai-subscriptions .gemini/skills/proxy-local-ai-subscriptions && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "proxy-local-ai-subscriptions" agent skill from https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions into .gemini/skills/proxy-local-ai-subscriptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-local-ai-subscriptions", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Peiiii/nextclaw proxy-local-ai-subscriptions

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/proxy-local-ai-subscriptions .github/skills/proxy-local-ai-subscriptions && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "proxy-local-ai-subscriptions" agent skill from https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions into .github/skills/proxy-local-ai-subscriptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-local-ai-subscriptions", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Peiiii/nextclaw proxy-local-ai-subscriptions --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/proxy-local-ai-subscriptions .opencode/skills/proxy-local-ai-subscriptions && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "proxy-local-ai-subscriptions" agent skill from https://github.com/Peiiii/nextclaw/tree/master/skills/proxy-local-ai-subscriptions into .opencode/skills/proxy-local-ai-subscriptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proxy-local-ai-subscriptions", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: proxy-local-ai-subscriptions
GitHub stars: 260
Token cost: ~1.9k tokens
SKILL.md length: 400 words
Files: 8 (incl. scripts)
Skills in repo: 70
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 5 steps: 先做只读检查 → 生成 localhost-only 配置 → 完成订阅 OAuth → …
Tasks that involve Linux administration
SKILL.md covers 安全边界, 工作流, 完成报告 and 故障与退出
Runs JavaScript scripts from its folder; calls brew and node

What it does

Proxy Local AI Subscriptions is an agent skill from Peiiii/nextclaw. 当用户希望把本机 Codex、ChatGPT Codex 或 Claude Code 订阅通过 localhost 暴露为 OpenAI 兼容端点，或希望在代理验证成功后把它添加成 NextClaw 自定义 provider 时使用。负责 CLIProxyAPI 安装检查、安全配置、OAuth 登录、Homebrew/systemd 持久托管、重启存活验收、NextClaw provider 事务式写入与 NCP 真实对话验收；不用于公网共享、转售、绕过配额或多用户账号池。

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts (for example `agents/openai.yaml` and `marketplace.json`).

It sits in Backend & APIs, covering Linux administration and OAuth and OpenID Connect. It works with OpenAI, Linux, Homebrew and macOS. The repository describes itself as: A human-centered long-term AI partner—not a task-centered assistant. The licence is MIT.

When your agent uses it

Tasks that involve Linux administration
Tasks that involve OAuth and OpenID Connect

Example prompts

“/proxy-local-ai-subscriptions”

Requirements

Node.js

Workflow steps

5 steps, taken from the step headings in SKILL.md.

先做只读检查
生成 localhost-only 配置
完成订阅 OAuth
启动并验证代理
询问是否接入 NextClaw

What it can do on your machine

Read from SKILL.md and the folder at commit 973722e. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 5 files in scripts/ (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
- brew
- node
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Proxy Local AI Subscriptions loads about 1.9k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 400 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~67
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteRuns commands with sudoSKILL.md:54

sudo -u <service-user> -H node scripts/cliproxy.mjs write-config \

NoteRuns commands with sudoSKILL.md:87
```
sudo -u <service-user> -H cliproxyapi \
```

NoteRuns commands with sudoSKILL.md:107

sudo node scripts/cliproxy.mjs install-systemd \

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Peiiii/nextclaw at commit 973722e, republished under its MIT licence (© Peiiii). 400 words, ~1,869 tokens.

Download SKILL.mdSave it as .claude/skills/proxy-local-ai-subscriptions/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.

name: proxy-local-ai-subscriptions
description: 当用户希望把本机 Codex、ChatGPT Codex 或 Claude Code 订阅通过 localhost 暴露为 OpenAI 兼容端点，或希望在代理验证成功后把它添加成 NextClaw 自定义 provider 时使用。负责 CLIProxyAPI 安装检查、安全配置、OAuth 登录、Homebrew/systemd 持久托管、重启存活验收、NextClaw provider 事务式写入与 NCP 真实对话验收；不用于公网共享、转售、绕过配额或多用户账号池。

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：

bash

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：

bash

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：

bash

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：

bash

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。

3. 完成订阅 OAuth

Codex：

bash

cliproxyapi \
  --config "$(brew --prefix)/etc/cliproxyapi.conf" \
  --codex-login

Claude Code：

bash

cliproxyapi \
  --config "$(brew --prefix)/etc/cliproxyapi.conf" \
  --claude-login

Linux 登录命令也必须以同一个 <service-user> 执行，并使用上一步的配置路径：

bash

sudo -u <service-user> -H cliproxyapi \
  --config <service-home>/.cli-proxy-api/cliproxyapi.conf \
  --codex-login

没有图形浏览器时加 --no-browser，把官方 OAuth URL 交给用户本人完成。不要读取、复制或展示 token 文件内容。默认只登录用户指定的一个账号；不要主动建立多账号轮询池。

4. 启动并验证代理

macOS Homebrew：

bash

brew services start cliproxyapi

如果服务已在运行且配置发生变化，先告知影响，再执行 brew services restart cliproxyapi。

Linux systemd：创建或更新 unit、启动服务会改变系统运行状态；先向用户说明影响并获得同意，然后使用 bundled script，禁止手写 unit：

bash

sudo node scripts/cliproxy.mjs install-systemd \
  --binary <absolute-cliproxyapi-path> \
  --config <service-home>/.cli-proxy-api/cliproxyapi.conf \
  --auth-dir <service-home>/.cli-proxy-api \
  --service-user <service-user> \
  --home <service-home>

脚本只管理带有本 skill marker 的 cliproxyapi.service；遇到已有非托管 unit 时默认停止，只有解释差异并取得明确同意后才能使用 --force。unit 固定 Restart=on-failure、WantedBy=multi-user.target，并在安装后验证 active、enabled、MainPID 与独立 cgroup。

先做就绪检查。macOS：

bash

node scripts/cliproxy.mjs check \
  --config "$(brew --prefix)/etc/cliproxyapi.conf" \
  --endpoint http://127.0.0.1:8317/v1 \
  --api-key-file "$HOME/.cli-proxy-api/nextclaw-api-key" \
  --service-manager homebrew \
  --service-name cliproxyapi

Linux：

bash

node scripts/cliproxy.mjs check \
  --config <service-home>/.cli-proxy-api/cliproxyapi.conf \
  --endpoint http://127.0.0.1:8317/v1 \
  --api-key-file <service-home>/.cli-proxy-api/nextclaw-api-key \
  --binary <absolute-cliproxyapi-path> \
  --service-manager systemd \
  --service-name cliproxyapi.service

从输出的 models 中选择真实存在的模型，再跑 Responses API 真实回复：

bash

node scripts/cliproxy.mjs smoke \
  --endpoint http://127.0.0.1:8317/v1 \
  --api-key-file "$HOME/.cli-proxy-api/nextclaw-api-key" \
  --model <raw-model-id>

首次 smoke 成功后，必须在用户已知会发生短暂中断的前提下执行一次托管重启验收。复用前述所有路径和 service 参数：

bash

node scripts/cliproxy.mjs restart-smoke \
  --config <config-path> \
  --endpoint http://127.0.0.1:8317/v1 \
  --api-key-file <api-key-file> \
  --model <raw-model-id> \
  --service-manager <homebrew-or-systemd> \
  --service-name <service-name> \
  --binary <cliproxyapi-path>

Homebrew 可省略 --binary；systemd 必须给绝对路径。只有 check.ok=true、lifecycle.active=true、lifecycle.enabled=true、模型列表非空，以及 restart-smoke.restartVerified=true 且回复精确命中 marker，才算代理可持续使用。Linux 还必须满足 lifecycle.independentFromNextclaw=true。失败时按 binary -> config safety -> service manager -> OAuth model list -> Responses API 顺序缩圈，不要跳过上游直连就改 NextClaw。

Show full SKILL.md (187 more words)Show less

5. 询问是否接入 NextClaw

代理真实回复成功后，必须明确询问：

本地 OpenAI 兼容端点已经验证成功。是否现在把它添加为 NextClaw provider？

用户没有明确同意时停止，不写 NextClaw 配置，也不改变默认模型。

接入前只选择一次 provider id，并在配置、模型 route 与 NCP 验收中始终复用它。provider id 是用户可自定义的 NextClaw 配置实例名，不是固定协议名：仅接 Codex 时推荐 codex-sub，仅接 Claude Code 时推荐 claude-sub；同一端点承载两类订阅时询问用户名称，推荐 local-ai-subscriptions。用户指定其他 kebab-case 名称时直接使用，不要改回预设名。

用户同意后执行：

bash

node scripts/nextclaw-provider.mjs \
  --endpoint http://127.0.0.1:8317/v1 \
  --api-key-file "$HOME/.cli-proxy-api/nextclaw-api-key" \
  --proxy-config <config-path> \
  --service-manager <homebrew-or-systemd> \
  --service-name <service-name> \
  --proxy-binary <cliproxyapi-path> \
  --provider-id <provider-id> \
  --display-name "<display-name>" \
  --model <raw-model-id>

脚本默认从 nextclaw status --json 读取当前 API 地址，并使用 wireApi=chat。macOS Homebrew 可省略 --proxy-binary；Linux systemd 必须传绝对路径。脚本会先调用同包 cliproxy.mjs check，选择真实模型后再强制执行一次 restart-smoke；未证明服务 active、enabled、独立托管且重启后真实回复成功时，在任何 provider API 请求前停止，因此不能绕过持久服务门禁。直接调用脚本且省略 --provider-id 时，为兼容既有用法仍默认 local-subscriptions；标准 skill 工作流必须显式传入上一步选定的 id，不能依赖该默认值。代理直连仍用 Responses API 证明 OpenAI 端点成立，但 NextClaw native 会携带工具定义；本次真实验收确认 Chat Completions wire 能保持工具 schema 兼容。脚本会先对候选配置执行真实 provider test，成功后才启用；新建 provider 在失败时自动删除回滚。若同名 provider 已指向其他端点，必须先解释冲突并获得同意，才可加 --replace-existing。

随后必须走 native session type 做一次 NCP 真实对话：

bash

node scripts/nextclaw-smoke.mjs \
  --model <provider-id>/<raw-model-id>

只有 provider test 和 NCP 最终回复都通过，才能说“已可在 NextClaw 使用”。不要因为 /api/health、模型列表或编译通过就宣告完成。

完成报告

报告以下事实，不输出任何 secret：

CLIProxyAPI 版本、配置路径、auth 目录、监听地址；
服务管理器、服务名、active/enabled 状态；Linux 还要报告独立 cgroup 与重启存活验收；
OAuth 类型（Codex 或 Claude），不要输出账号 token；
真实验证的 raw model id 与 OpenAI wire；
实际创建/更新的 provider id 与 display name；
NCP session type 必须是 native，模型必须复用同一个 <provider-id>/<raw-model-id>；
未验证的平台或能力（例如本次只验 Codex，就明确 Claude 未做真实验收）。

故障与退出

check 报非 localhost 配置：停止服务并修复绑定；不要带风险继续。
check 报服务未 active/enabled 或 cgroup 不独立：停止 provider 接入，使用对应服务管理器修复；不要用 nohup 临时补位。
restart-smoke 失败：保持或恢复代理服务，报告持久性验收未完成；不得创建 provider。
/v1/models 为空：重新执行对应 OAuth 登录并检查 auth 目录，不要猜模型名。
代理直连成功但 provider test 失败：检查 apiBase 是否带 /v1、模型是否 provider-scoped、wireApi 是否为 chat。
provider test 成功但 NCP 失败：按 NextClaw NCP SSE 链路排查；不要把问题归因成 OAuth 已失效。
删除 provider、恢复备份配置、注销 OAuth 或卸载 CLIProxyAPI 都是破坏性动作，只在用户明确要求后执行。

Files

SKILL.md and 7 other files (scripts) in skills/proxy-local-ai-subscriptions of Peiiii/nextclaw.

SKILL.md
agents/openai.yaml
marketplace.json
scripts/cliproxy-service.mjs
scripts/cliproxy.mjs
scripts/local-subscription-proxy.utils.mjs
scripts/nextclaw-provider.mjs
scripts/nextclaw-smoke.mjs

Open the folder on GitHubat commit 973722e

Compare with similar skills

Proxy Local AI Subscriptions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Proxy Local AI Subscriptions compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Proxy Local AI Subscriptions this skillPeiiii/nextclaw	260	—	~1.9k	Automated safety check: Notes	MIT	yesterday
Install Mimi Remotegaixianggeng/mimi-remote	104	—	~2.8k	Automated safety check: Pass	GPL-3.0	today
Openclaw Live Updateropenclaw/openclaw	392k	—	~3.7k	Automated safety check: Pass	MIT	today
Agentdock User Guideuvwt/agentdock	1.2k	—	~1.6k	Automated safety check: Pass	Apache-2.0	yesterday
Shadowvpn Deploy Clientmadeye/shadowvpn	101	—	~2.4k	Automated safety check: Notes	MIT	1 mo ago
Agent Chatprofbernardoj/everclaw-community-branches	112	—	~2.2k	Automated safety check: Notes	MIT	1 mo ago

Similar skills

Install Mimi Remote
gaixianggeng/mimi-remote
安装、配置、配对、迁移、升级、诊断、回滚或卸载 Mimi Remote；在 macOS 上安装和维护 Mimi Remote Mac 菜单栏 App / DMG，或通过 Homebrew、Linux user-systemd 部署 agentd；从源码构建 iPhone/iPad App；配置 Codex 主通道和可选 Claude Code 实验 Runtime。用户提出“安装 Mimi…
104 GitHub stars~2.8k tokensUpdated today
MobileAuto-check passed
Openclaw Live Updater
openclaw/openclaw
Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.
392k GitHub stars~3.7k tokensUpdated today
DevOps & CloudAuto-check passed
Agentdock User Guide
uvwt/agentdock
当用户询问 AgentDock 是什么、如何使用、配置在哪里、不同平台或安装方式怎样修改配置并生效、如何重启或验证配置、如何发现并配置 Codex/Claude/Grok 等 Coding Agent 的 ACP，以及常见运行问题时使用；覆盖 macOS Desktop、Windows Desktop、Linux 服务、Docker 和直接运行二进制，不用于源码开发与贡献流程。
1.2k GitHub stars~1.6k tokensUpdated yesterday
DevOps & CloudAuto-check passed
Shadowvpn Deploy Client
madeye/shadowvpn
Deploy, install, and run the ShadowVPN client in a target environment — Linux (systemd), macOS (launchd), or Windows (Wintun, foreground launcher or scheduled-task service).
101 GitHub stars~2.4k tokensUpdated 1 mo ago
Productivity & AutomationAuto-check: notes
Agent Chat
profbernardoj/everclaw-community-branches
XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw.
112 GitHub stars~2.2k tokensUpdated 1 mo ago
DevOps & CloudAuto-check: notes
Install Watchdog
athola/claude-night-market
Installs egregore watchdog daemon via launchd or systemd for autonomous relaunching.
342 GitHub stars~837 tokensUpdated 2 days ago
DevOps & CloudAuto-check passed

More from Peiiii/nextclaw

All 70 skills in this repo

Nextclaw Skin Studio
Peiiii/nextclaw
A skill your agent uses when a user wants to browse, apply, inspect, create, refine, switch, or remove a NextClaw skin; wants a personal skin with arbitrary CSS, JavaScript, images, SVG, DOM…
260 GitHub stars~1.8k tokensUpdated yesterday
Auto-check passed
Development Task Telemetry
Peiiii/nextclaw
A skill your agent uses when a development task needs visible phase tracing, task-level or phase-level Token measurement, model/effort comparison, or a deterministic usage report or local dashboard…
260 GitHub stars~802 tokensUpdated yesterday
Auto-check passed
Nextclaw Product Visual Assets
Peiiii/nextclaw
当 NextClaw 产品更新后需要生成、替换、挑毛病或检查官网、GitHub README、用户文档或社交传播中的真实截图、AI 宣传视觉、整页 HTML 宣传预览、社区二维码等对外视觉资产时使用；也用于“更新截图”“重新截一批图”“做宣传页”“生成 campaign 页面”“视觉审稿”“五星挑刺法”或发布前检查视觉资产。普通站点布局开发或只写文章不触发。
260 GitHub stars~801 tokensUpdated yesterday
Auto-check passed
UI UX Pro Max
Peiiii/nextclaw
A skill your agent uses when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset…
260 GitHub stars~2k tokensUpdated yesterday
Auto-check passed
Impeccable
Peiiii/nextclaw
A skill your agent uses when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable…
260 GitHub stars~2.5k tokensUpdated yesterday
Auto-check passed
Nextclaw Skill Resource Hub
Peiiii/nextclaw
Curate NextClaw skill resources, including OpenClaw and community sources.
260 GitHub stars~479 tokensUpdated yesterday
Auto-check passed

Works with

Questions about Proxy Local AI Subscriptions

What does Proxy Local AI Subscriptions do?

When should I use Proxy Local AI Subscriptions?

Proxy Local AI Subscriptions fits situations like: tasks that involve Linux administration; tasks that involve OAuth and OpenID Connect.

How do I install Proxy Local AI Subscriptions in Claude Code?

Run `npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a claude-code`. Or copy the skill folder (skills/proxy-local-ai-subscriptions in Peiiii/nextclaw) into .claude/skills/proxy-local-ai-subscriptions in your project. Claude Code loads it when a task matches its description.

How do I install Proxy Local AI Subscriptions in Codex?

Run `npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a codex`. Or copy the skill folder (skills/proxy-local-ai-subscriptions in Peiiii/nextclaw) into .agents/skills/proxy-local-ai-subscriptions in your project. Codex loads it when a task matches its description.

Can I use Proxy Local AI Subscriptions in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Peiiii/nextclaw --skill proxy-local-ai-subscriptions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proxy-local-ai-subscriptions, .gemini/skills/proxy-local-ai-subscriptions, .github/skills/proxy-local-ai-subscriptions and .opencode/skills/proxy-local-ai-subscriptions in your project.

What does Proxy Local AI Subscriptions need to run?

Going by SKILL.md and its folder, Proxy Local AI Subscriptions needs JavaScript for the scripts in its folder and the command-line tools its instructions call (brew and node). Our summary lists: Node.js.

Does Proxy Local AI Subscriptions access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Proxy Local AI Subscriptions safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Proxy Local AI Subscriptions use?

Proxy Local AI Subscriptions is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Proxy Local AI Subscriptions use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Proxy Local AI Subscriptions?

Skills that share tags, products or a category with Proxy Local AI Subscriptions: Install Mimi Remote (gaixianggeng/mimi-remote, 104 stars), Openclaw Live Updater (openclaw/openclaw, 392k stars), Agentdock User Guide (uvwt/agentdock, 1.2k stars) and Shadowvpn Deploy Client (madeye/shadowvpn, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Proxy Local AI Subscriptions?

Peiiii (a GitHub user) maintains it in Peiiii/nextclaw, which has 260 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 7, 2026.

Source: Peiiii/nextclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Proxy Local AI Subscriptions

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Proxy Local AI Subscriptions

安全边界

工作流

1. 先做只读检查

2. 生成 localhost-only 配置

3. 完成订阅 OAuth

4. 启动并验证代理

5. 询问是否接入 NextClaw

完成报告

故障与退出

Files

Compare with similar skills

Similar skills

More from Peiiii/nextclaw

Related

Questions about Proxy Local AI Subscriptions