What is cli-anything?

A tool-building workflow that turns software controlled through a graphical interface—such as GIMP or Blender—into a command-line tool. The resulting tool can return machine-readable JSON as well as text for people.

Use it to create or refine command-line interfaces for applications, internal admin systems, or browser-control tools. It can also generate tests, validate the interface, and prepare it for installation.

It lets an AI agent operate desktop applications through commands instead of relying on clicks and screen layouts. It also covers planning, implementation, testing, documentation, and packaging.

cli-anything — Skill for Claude Code and Codex by djblack1209-coder: A tool-building workflow that turns software controlled through a…

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/djblack1209-coder/openclaw-bot/cli-anything

Any agent

npx skills add djblack1209-coder/OpenClaw-Bot --skill cli-anything

Clone the repo

git clone --depth 1 https://github.com/djblack1209-coder/OpenClaw-Bot

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 789 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.

Model	Per session	Once invoked
Fable 5	$0.00037	$0.00789
Opus 5	$0.00018	$0.00394
Sonnet 5	$0.00007	$0.00158
Haiku 4.5	$0.00004	$0.00079

Measured 3d ago against content hash c0e02fb438ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-anything 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 3d 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.

apps/openclaw/skills/cli-anything/SKILL.md · 99 lines

What it actually says

CLI-Anything 集成

让任意 GUI 软件变成 Agent 可控的 CLI 工具。

核心能力

分析软件源码/API，自动生成完整 CLI 接口
7 阶段自动化流水线: 分析→设计→实现→测试计划→写测试→文档→发布
生成的 CLI 支持 JSON 输出（Agent 友好）+ 人类可读格式
内置 REPL 交互模式
已验证 13 个应用: GIMP、Blender、LibreOffice、OBS、Audacity 等

安装

git clone https://github.com/HKUDS/CLI-Anything.git
mkdir -p ~/.openclaw/skills/cli-anything
cp CLI-Anything/openclaw-skill/SKILL.md ~/.openclaw/skills/cli-anything/SKILL.md

使用方式

为软件生成 CLI

@cli-anything build a CLI for ./gimp
@cli-anything build a CLI for https://github.com/some/app

细化已有 CLI

@cli-anything refine ./gimp "批量处理和滤镜"

验证 CLI 质量

@cli-anything validate ./gimp

7 阶段流水线

🔍 分析 — 扫描源码，映射 GUI 操作到 API
📐 设计 — 架构命令组、状态模型、输出格式
🔨 实现 — 构建 Click CLI + REPL + JSON 输出 + 撤销/重做
📋 测试计划 — 创建 TEST.md（单元 + E2E）
🧪 写测试 — 实现完整测试套件
📝 文档 — 更新 TEST.md 和结果
📦 发布 — 创建 setup.py，安装到 PATH

OpenClaw Bot 集成场景

控制内部管理台

# 为内部 Web 管理台生成 CLI
@cli-anything build a CLI for an internal web admin interface

# Agent 可以直接操作
cli-anything-admin records list --status pending --json
cli-anything-admin records show --id example --json

控制浏览器自动化

# 为 Chrome DevTools Protocol 生成 CLI
@cli-anything build a CLI for chrome-devtools

# 替代 Playwright 脚本
cli-anything-chrome tab new --url "https://x.com"
cli-anything-chrome element click --selector "#post-button"

控制本地开发工具

# 为 VS Code 生成 CLI
cli-anything-vscode file open --path ./src/index.ts
cli-anything-vscode terminal run --command "npm test"

触发条件

严总说 "cli-anything"、"生成 CLI"、"让 Agent 控制 xxx"
需要自动化操作某个 GUI 软件时
/coding_agent 任务涉及 GUI 软件交互时

注意

需要 Python 3.10+
目标软件需要已安装在本机
生成的 CLI 通过 pip install -e . 安装到 PATH
每个 CLI 命名为 cli-anything-<软件名>

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.

3d ago First seen · 99 lines · 37 tokens per session scan A c0e02fb438ee

Subscribe to this mod's changes

cli-anything is a skill published in the GitHub repository djblack1209-coder/OpenClaw-Bot (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 37 tokens to every session and 789 once invoked, about $0.0002 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 2026-08-31.

Backend and APIs Building agents ai-agents automation fastapi llm-routing open-source

transcribe-filing

Transcribe an insurance rate filing or internal rating manual into an OpenRater workbook, then validate, build, verify, and rate it through the OpenRater MCP tools. Use when the user shares a filing/manual (PDF or pages) and wants it executable — "build this filing", "digitize this rating manual", "make this rateable"…

vadim-filimonov/openrater · 102 tokens

cli-anything