File: README.md Copy Chapter

  CLI-Anything: Making ALL Software Agent-Native

🌐 CLI-Hub: pip install cli-anything-hub then cli-hub install <name> — browse, install, and manage all community-built CLIs. Want to add your own? Open a PR — the hub updates instantly.

🎬 See Demos: Watch AI agents use generated CLIs plus preview, live preview, and trajectory loops to produce real artifacts — CAD builds, 3D scenes, diagrams, gameplay, subtitles, and more.

🙋 [Become a Contributor, or Request a CLI]: Join us! Sign up to build a new CLI harness — once reviewed and merged, you'll gain access as one of our community contributors! Wish CLI-Anything supported a specific software or service? Submit a wishlist request!

One Command Line: Make any software agent-ready for Pi, OpenClaw, nanobot, Cursor, Claude Code, etc.  中文文档 | 日本語ドキュメント | Deutsch

📰 News Copy Chapter

Thanks to all invaluable efforts from the community! More updates continuously on the way everyday..

• 2026-05-30 🧭 Hermes skill proposed (#320), adding a CLI-Anything orchestration skill with installer scripts and HARNESS fallback guidance. 🗺️ ArcGIS Pro was proposed for the public registry (#318) as a Windows/ArcPy CLI for cartography, geoprocessing, feature editing, and live-Pro MCP workflows.

• 2026-05-27 🔧 CLI-Hub registry date updates now handle python -m pip install commands (#312), improving package-date detection for registry automation.

• 2026-05-23 📝 Obsidian Agent CLI was proposed for the public registry (#307), bringing a PyPI-installed Obsidian automation CLI with persistent agent memory workflows and a pinned skill link.

• 2026-05-21 🔒 Sketch CLI token-file handling was hardened against path traversal and symlink escapes (#304).

• 2026-05-20 📓 Joplin CLI was proposed (#300) with notebooks, notes, to-dos, tags, attachments, search/sync, import/export, server/E2EE helpers, full docs, packaged skill docs, and a 134-test validation baseline.

• 2026-05-20 🎛️ Rekordbox CLI merged (#252) with guarded SQLCipher write paths, backup-required forced writes, smoke coverage, and root skill sync. 📚 Calibre CLI merged (#223) with library/search/metadata/conversion/export workflows, 41 unit tests, real-Calibre E2E evidence, and root skill validation. 🧊 3MF CLI merged (#209) with mesh inspection, hole resizing, repair, comparison, and preserved triangle attributes. 🎙️ MiniMax CLI merged (#189) with chat/TTS workflows, JSON-safe model/voice listing, REPL quote handling, and smoke/E2E coverage. 🎮 UEAtelier joined the registry (#297) as an Unreal Editor MCP self-extension workbench with a Python CLI proxy.

• 2026-05-19 🛠️ Existing harnesses got a quality/security pass — Zoom downloads recordings from direct URLs (#294), Obsidian search now uses the Local REST API vendor content types (#289), LibreOffice headless conversion is more robust on macOS (#290), and XML/SVG/ODF/MLT/MusicXML/CSL parsing now routes untrusted input through defusedxml (#296).

• 2026-05-18 📈 README presentation refreshed with the Trendshift badge and centered project header polish (#285, #286), keeping the landing section focused on discovery and project momentum.

• 2026-05-17 🌐 CLI-Hub registry handling was hardened (#281) — registry entries are now copied before _source tagging, preventing cached or mocked registry data from being mutated in place.

• 2026-05-16 🔧 n8n received the REPL banner crash fix that later merged into main (#280), restoring the no-subcommand interactive startup path with regression coverage.

Earlier news (Apr 10–18)

• 2026-04-18 🧩 All SKILL.md files are now being unified under the top-level skills/ directory — every CLI skill can be installed from one canonical source with npx skills add HKUDS/CLI-Anything --skill <skill-name> -g -y. We also added root-skill validation CI, synced contribution / PR docs and REPL skill-path hints to the new layout, and refreshed the CLI-Hub install-first frontend around the new npx skills flow.

• 2026-04-17 🌐 CLI-Hub received another install UX pass — public registry metadata and skill coverage were tightened, visit counting was corrected, and the web hub was further refined. 🧪 Shotcut render output duration was fixed (#92). 📝 SKILL contribution paths were corrected for the new docs flow (#224), and the skill generator now safely handles empty intros (#203).

• 2026-04-16 🗺️ QGIS CLI merged (#207) — a full GIS / map authoring harness landed. 🧬 UniMol Tools CLI merged (#219) for molecular modeling workflows. 🌐 CLI-Hub also added more public CLIs, including py4csr, refreshed its generated meta-skill, corrected SKILL contribution docs, and fixed apt-get package extraction in skill generation (#204).

• 2026-04-16 📈 Unreal Insights CLI expanded — added background capture session control (capture start/status/snapshot/stop), engine-root-matched UnrealInsights.exe resolution/build flows, and refreshed docs/tests for the new orchestration workflow.

• 2026-04-15 🌐 CLI-Hub updated to v0.2.0 — the PyPI package now supports public CLIs from multiple install sources (pip, npm, brew, bundled/system tools), backed by a new public_registry.json. The Hub frontend was redesigned with separate CLI-Anything CLIs and Public CLIs decks, and live end-to-end checks now cover real install, update, and uninstall flows across both pip and npm packages.

• 2026-04-14 🧭 Safari CLI merged (#212) and added to the Hub registry — browser automation via safari-mcp. 🎬 Kdenlive also received compatibility fixes for Gen 5 project output and invalid project generation.

• 2026-04-13 📓 Obsidian CLI merged (#211) — knowledge management harness via the Local REST API, with 48 unit tests and 7 E2E tests. ⛓️ Eth2-Quickstart CLI merged (#195) — Ethereum staking node management harness. 📚 Zotero CLI updated to v0.4.1 (#201) — now shipped from its standalone repo, and CLI-Hub gained support for remote skill_md URLs.

• 2026-04-11 🔗 n8n CLI merged (#188) — workflow automation harness for self-hosted automation flows. 🔧 Exa CLI fix (#205) added the x-exa-integration header for usage tracking. 📦 CLI-Hub also gained its PyPI auto-publish workflow and package refresh pipeline.

• 2026-04-10 📦 CLI-Hub package manager launched — pip install cli-anything-hub to browse, search, install, update, and uninstall CLI-Anything harnesses from one command. The web Hub also shipped its first install-focused frontend refresh and "Empower yourself" toolkit card.

Earlier news (Apr 1–9)

• 2026-04-09 🧹 Cleanup and docs pass (#200) — fixed Openscreen test subtotals, added Openscreen to the Chinese README and project structure, and clarified /cli-anything command syntax in the docs.

• 2026-04-08 🎬 Openscreen CLI merged (#183) — screen recording editor harness with 101 tests. ☁️ CloudAnalyzer CLI merged (#181) — cloud cost analysis harness with 27 commands. 🌊 SeaClip / PM2 / ChromaDB harnesses merged (#129).

• 2026-04-07 🔄 Dify Workflow CLI merged (#191) — workflow automation wrapper. 🔧 Inkscape auto-save fix (#193, fixes #182). 🛡️ DomShell security hardening (#156) — URL validation and DOM sanitization for the browser CLI. 🥧 Pi Coding Agent extension merged (#178).

• 2026-04-06 🔍 Exa CLI merged (#172) — AI-powered web search and answers harness. 🎮 Godot CLI merged (#140) — game engine harness with a full demo-game E2E pipeline. ☁️ CloudAnalyzer review fixes and frontend improvements also landed.

• 2026-04-03 🧪 WireMock CLI merged (#170) — HTTP mock server harness for API testing. 🥧 Pi Coding Agent extension support also landed, and CLI demo recordings were added to the docs.

• 2026-04-01 ⚔️ Slay the Spire II CLI merged (#148) — deck-building roguelike harness. 🎥 VideoCaptioner CLI merged (#166) — AI-powered video captioning harness. 🛰️ IntelWatch was added to the registry for B2B OSINT workflows.

Earlier news (Mar 23–30)

• 2026-03-30 🏗️ CLI-Anything v0.2.0 — HARNESS.md progressive disclosure redesign. Detailed guides extracted into guides/ for on-demand loading. Phases 1–7 now contiguous. Key Principles and Rules merged into a single authoritative section.

• 2026-03-29 📐 Blender skill docs updated — enforce absolute render paths and correct prerequisites.

• 2026-03-28 🌐 CLIBrowser added to CLI-Hub registry for agent-accessible browser automation.

• 2026-03-27 📚 Zotero SKILL.md enhanced with agent-facing constraints; REPL config and executable resolution fixes.

• 2026-03-26 📖 Zotero CLI harness landed for Zotero desktop (library management, collections, citations). Draw.io custom ID bugfix (#132) and registry.json syntax fix.

• 2026-03-25 🎮 RenderDoc CLI merged for GPU frame capture analysis. FreeCAD updated for v1.1. Blender EEVEE engine name corrected. Zoom token permissions hardened.

• 2026-03-24 🏭 FreeCAD CLI added with 258 commands across 17 groups. iTerm2 and Teltonika RMS harnesses added to registry.

• 2026-03-23 🤖 Launched CLI-Hub meta-skill — agents can now discover and install CLIs autonomously. Krita CLI harness merged for digital painting.

Earlier news (Mar 11–22)

• 2026-03-22 🎵 MuseScore CLI merged with transpose, export, and instrument management.

• 2026-03-21 🔧 Infrastructure improvements — refined test harnesses and documentation across multiple CLIs. Enhanced Windows compatibility for several backends.

• 2026-03-20 🌐 Novita AI CLI added for OpenAI-compatible API access. Registry metadata improvements for better hub discovery.

• 2026-03-19 📦 Package structure refinements across harnesses. Improved SKILL.md generation with better command documentation.

• 2026-03-18 🧪 Test coverage expansion — additional E2E scenarios and edge case validation across multiple CLIs.

• 2026-03-17 🌐 Launched the CLI-Hub — a central registry where you can browse, search, and install any CLI with a single pip command.

• 2026-03-16 🤖 Added SKILL.md generation (Phase 6.5) — every generated CLI now ships with an AI-discoverable skill definition.

• 2026-03-15 🐾 Support for OpenClaw from the community! Merged Windows cygpath guard for cross-platform support.

• 2026-03-14 🔒 Fixed a GIMP Script-Fu path injection vulnerability and added Japanese README translation.

• 2026-03-13 🔌 Qodercli plugin officially merged as a community contribution with dedicated setup scripts.

• 2026-03-12 📦 Codex skill integration landed, bringing CLI-Anything to yet another AI coding platform.

• 2026-03-11 📞 Zoom video conferencing harness added as the 11th supported application.

🤔 Why CLI? Copy Chapter

CLI is the universal interface for both humans and AI agents:

• Structured & Composable - Text commands match LLM format and chain for complex workflows

• Lightweight & Universal - Minimal overhead, works across all systems without dependencies

• Self-Describing - --help flags provide automatic documentation agents can discover

• Proven Success - Claude Code runs thousands of real workflows through CLI daily

• Agent-First Design - Structured JSON output eliminates parsing complexity

• Deterministic & Reliable - Consistent results enable predictable agent behavior

🚀 Quick Start Copy Chapter

CLI-Anything has two equally useful starting points:

Phase 1: Empower yourself — your CLI toolkit

Install the CLI-Hub package manager first. It lets you browse, search, inspect, install, update, uninstall, and launch CLI-Anything harnesses plus public third-party CLIs from one command.

PIP

pip install cli-anything-hub

# Browse what is available
cli-hub list
cli-hub search image

# Install and try a CLI immediately
cli-hub install gimp
cli-hub info gimp
cli-hub launch gimp

Some CLIs wrap real desktop or backend software. If a selected CLI needs GIMP, Blender, LibreOffice, or another upstream tool, install that upstream application too.

Phase 1.5: Empower your agents — install in one command

Give SKILL-compatible agents the CLI-Hub meta-skill so they can discover and install the right CLI for a task.

Also available on: ClawHub, SkillHub, SkillHub.cn

NPX SKILLS

npx skills add HKUDS/CLI-Anything --skill cli-hub-meta-skill -g -y

Works with: OpenClaw, Nanobot, Claude Code, Codex, Reasonix, Antigravity, and other SKILL-compatible agents.

Then prompt:

Find appropriate CLI software in CLI-Hub and complete the task: ...

Phase 3: Build a new CLI when the registry does not have one yet

Use the CLI-Anything generator when you need a new harness for software, a codebase, or an internal tool that is not already available through CLI-Hub.

Prerequisites

• Python 3.10+
• Target software or source repo available locally or online
• A supported AI coding agent: Claude Code | Pi | OpenClaw | OpenCode | Codex | Hermes | Reasonix | Qodercli | GitHub Copilot CLI | More Platforms

Pick Your Agent Platform Copy Section

⚡ Claude Code

Step 1: Add the Marketplace

CLI-Anything is distributed as a Claude Code plugin marketplace hosted on GitHub.

# Add the CLI-Anything marketplace
/plugin marketplace add HKUDS/CLI-Anything

Step 2: Install the Plugin

# Install the cli-anything plugin from the marketplace
/plugin install cli-anything

That's it. The plugin is now available in your Claude Code session.

Note for Win Users: Claude Code runs shell commands via bash. On Windows, install Git for Windows (includes bash and
cygpath) or use WSL; otherwise commands may fail with cygpath: command not found.

Step 3: Build a CLI in One Command

# /cli-anything <software-path-or-repo>
# Generate a complete CLI for GIMP (all 7 phases)
/cli-anything ./gimp

Command compatibility across Claude Code versions:

• Use /cli-anything as the primary entrypoint.
• On older builds where /cli-anything isn't recognized after confirming the plugin is installed and loaded, try the legacy entry form /cli-anything:cli-anything.
• Auxiliary commands keep the :subcommand form (e.g. /cli-anything:refine).

If you see Unknown skill: cli-anything, focus on plugin install/load first (both entry forms reference the same skill, so swapping forms won't help):

1. Reload plugin commands: /reload-plugins
2. Verify the plugin is loaded: /help cli-anything (CLI-Anything help/commands should appear)
3. Reinstall from marketplace if needed:
   • /plugin marketplace add HKUDS/CLI-Anything
   • /plugin install cli-anything
4. After confirming the plugin is available, retry the entry command:
   • Preferred: /cli-anything ./gimp
   • Older builds only: /cli-anything:cli-anything ./gimp

This runs the full pipeline:

1. 🔍 Analyze — Scans source code, maps GUI actions to APIs
2. 📐 Design — Architects command groups, state model, output formats
3. 🔨 Implement — Builds Click CLI with REPL, JSON output, undo/redo
4. 📋 Plan Tests — Creates TEST.md with unit + E2E test plans
5. 🧪 Write Tests — Implements comprehensive test suite
6. 📝 Document — Updates TEST.md with results
7. 📦 Publish — Creates setup.py, installs to PATH

Step 4 (Optional): Refine and Improve the CLI

After the initial build, you can iteratively refine the CLI to expand coverage and add missing capabilities:

# Broad refinement — agent analyzes gaps across all capabilities
/cli-anything:refine ./gimp

# Focused refinement — target a specific functionality area
/cli-anything:refine ./gimp "I want more CLIs on image batch processing and filters"

The refine command performs gap analysis between the software's full capabilities and current CLI coverage, then implements new commands, tests, and documentation for the identified gaps. You can run it multiple times to steadily expand coverage — each run is incremental and non-destructive.

Alternative: Manual Installation

If you prefer not to use the marketplace:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git

# Copy plugin to Claude Code plugins directory
cp -r CLI-Anything/cli-anything-plugin ~/.claude/plugins/cli-anything

# Reload plugins
/reload-plugins

⚡ Pi Coding Agent

Step 1: Install the Extension

The extension lives at .pi-extension/cli-anything/ in this repository. Install it globally so /cli-anything commands are available in all Pi projects:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git
cd CLI-Anything

# Install globally into Pi's extensions directory
bash .pi-extension/cli-anything/install.sh

To uninstall:

bash .pi-extension/cli-anything/install.sh --uninstall

How it works: install.sh copies the extension files (including HARNESS.md, commands, guides, scripts, and templates from cli-anything-plugin/) into ~/.pi/agent/extensions/cli-anything/, which Pi auto-discovers on startup. Run /reload in Pi or restart Pi to activate.

Step 2: Build a CLI in One Command

Once the extension is loaded, the following commands are available:

# Generate a complete CLI for GIMP (all 7 phases)
/cli-anything ./gimp

# Build from a GitHub repo
/cli-anything https://github.com/blender/blender

Step 3 (Optional): Refine and Improve the CLI

# Broad refinement — agent analyzes gaps across all capabilities
/cli-anything:refine ./gimp

# Focused refinement — target a specific functionality area
/cli-anything:refine ./gimp "batch processing and filters"

Available Commands

⚡ OpenCode (Experimental)

Step 1: Install the Commands

Note: Please upgrade to the latest OpenCode. Older versions may use a different commands path.

Copy the CLI-Anything commands and HARNESS.md to your OpenCode commands directory:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git

# Global install (available in all projects)
cp CLI-Anything/opencode-commands/*.md ~/.config/opencode/commands/
cp CLI-Anything/cli-anything-plugin/HARNESS.md ~/.config/opencode/commands/

# Or project-level install
cp CLI-Anything/opencode-commands/*.md .opencode/commands/
cp CLI-Anything/cli-anything-plugin/HARNESS.md .opencode/commands/

Note: Please upgrade to the latest OpenCode. Older versions use command/ (singular) instead of commands/. If commands/ does not exist, use command/ for both global and project-level installs.

Note: HARNESS.md is the methodology spec that all commands reference. It must be in the same directory as the commands.

This adds 5 slash commands: /cli-anything, /cli-anything-refine, /cli-anything-test, /cli-anything-validate, and /cli-anything-list.

Step 2: Build a CLI in One Command

# Generate a complete CLI for GIMP (all 7 phases)
/cli-anything ./gimp

# Build from a GitHub repo
/cli-anything https://github.com/blender/blender

The command runs as a subtask and follows the same 7-phase methodology as Claude Code.

Step 3 (Optional): Refine and Improve the CLI

# Broad refinement — agent analyzes gaps across all capabilities
/cli-anything-refine ./gimp

# Focused refinement — target a specific functionality area
/cli-anything-refine ./gimp "batch processing and filters"

⚡ Goose (Desktop / CLI) ^{`Experimental` `Community`}

Step 1: Install Goose

Install Goose (Desktop or CLI) using the official Goose instructions for your OS.

Step 2: Configure a CLI Provider

Configure Goose to use a CLI provider such as Claude Code, and make sure that CLI is installed and authenticated.

Step 3: Use CLI-Anything in a Goose Session

Once Goose is configured, start a session and use the same CLI-Anything commands described above for Claude Code, for example:

/cli-anything ./gimp
/cli-anything:refine ./gimp "batch processing and filters"

Note: When Goose runs through a CLI provider, it uses that provider's capabilities and command format.

⚡ Qodercli ^`Community`

Step 1: Register the Plugin

git clone https://github.com/HKUDS/CLI-Anything.git
bash CLI-Anything/qoder-plugin/setup-qodercli.sh

This registers the cli-anything plugin in ~/.qoder.json. Start a new Qodercli session after registration.

Step 2: Use CLI-Anything from Qodercli

/cli-anything ./gimp
/cli-anything:refine ./gimp "batch processing and filters"
/cli-anything:validate ./gimp

⚡ OpenClaw ^`Community`

Step 1: Install the Skill

CLI-Anything provides a native OpenClaw SKILL.md file. Copy it to your OpenClaw skills directory:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git

# Install to the global skills folder
mkdir -p ~/.openclaw/skills/cli-anything
cp CLI-Anything/openclaw-skill/SKILL.md ~/.openclaw/skills/cli-anything/SKILL.md

Step 2: Build a CLI

Now you can invoke the skill inside OpenClaw:

@cli-anything build a CLI for ./gimp

The skill follows the same 7-phase methodology as Claude Code and OpenCode.

⚡ Codex ^{`Experimental` `Community`}

Step 1: Install the Skill

Run the bundled installer:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git

# Install the skill
bash CLI-Anything/codex-skill/scripts/install.sh

On Windows PowerShell, use:

.\CLI-Anything\codex-skill\scripts\install.ps1

This installs the skill to $CODEX_HOME/skills/cli-anything (or ~/.codex/skills/cli-anything if CODEX_HOME is unset).
The installer also vendors the canonical HARNESS.md, command specifications,
on-demand guides, reusable helper scripts, skill template, and preview protocol
into the installed skill's references/ and scripts/ directories.
This keeps the Codex skill self-contained while using cli-anything-plugin/ as
the source of truth.

Restart Codex after installation so it is discovered.

Step 2: Use CLI-Anything from Codex

Describe the task in natural language, for example:

Use CLI-Anything to build a harness for ./gimp
Use CLI-Anything to refine ./shotcut for picture-in-picture workflows
Use CLI-Anything to validate ./libreoffice
Use CLI-Anything to list generated harnesses under the current directory

The Codex skill adapts the same methodology used by the Claude Code plugin and
OpenCode commands, while keeping the generated Python harness format unchanged.

To verify the self-contained Codex installation locally:

bash CLI-Anything/codex-skill/tests/test_install.sh

⚡ Hermes ^{`Experimental` `Community`}

Step 1: Install the Skill

Run the bundled installer:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git

# Install the skill
bash CLI-Anything/hermes-skill/scripts/install.sh

On Windows PowerShell, use:

.\CLI-Anything\hermes-skill\scripts\install.ps1

This installs the skill to $HERMES_HOME/skills/cli-anything-hermes (or ~/.hermes/skills/cli-anything-hermes if HERMES_HOME is unset).

Restart Hermes Agent after installation so it is discovered.

Step 2: Use CLI-Anything from Hermes

Describe the task in natural language, for example:

Use CLI-Anything to build a harness for ./gimp
Use CLI-Anything to refine ./shotcut for picture-in-picture workflows
Use CLI-Anything to validate ./libreoffice

The Hermes skill adapts the same methodology used by the Claude Code plugin and
Codex skill, binding Hermes's terminal, execute_code, delegate_task, and
read_file / write_file / patch tools to the 7-phase harness workflow while
keeping the generated Python harness format unchanged.

⚡ Reasonix ^{`Experimental` `Community`}

Step 1: Install the Skill

Run the bundled installer:

# Clone the repo
git clone https://github.com/HKUDS/CLI-Anything.git

# Install the skill
bash CLI-Anything/reasonix-skill/scripts/install.sh

On Windows PowerShell, use:

.\CLI-Anything\reasonix-skill\scripts\install.ps1

This installs the skill to Reasonix's global skill directory at ~/.reasonix/skills/cli-anything.

Restart Reasonix after installation so it is discovered.

Step 2: Use CLI-Anything from Reasonix

Describe the task in natural language, for example:

Use CLI-Anything to build a harness for ./gimp
Use CLI-Anything to refine ./shotcut for picture-in-picture workflows
Use CLI-Anything to validate ./libreoffice

The Reasonix skill adapts the same methodology used by the Claude Code plugin and
Codex/Hermes skills, binding Reasonix's bash, write_file, edit_file,
multi_edit, grep, glob, and optional mcp__codegraph__search / mcp__codegraph__context tools to the
7-phase harness workflow while keeping the generated Python harness format unchanged.

⚡ GitHub Copilot CLI ^`Community`

Step 1: Install the Plugin

git clone https://github.com/HKUDS/CLI-Anything.git
cd CLI-Anything
copilot plugin install ./cli-anything-plugin

This installs the CLI-Anything plugin to GitHub Copilot CLI. The plugin should now be available in your GitHub Copilot CLI session.

Step 2: Use CLI-Anything from GitHub Copilot CLI

/cli-anything ./gimp
/cli-anything:refine ./gimp "batch processing and filters"
/cli-anything:validate ./gimp

🔮 More Platforms (Coming Soon)

CLI-Anything is designed to be platform-agnostic. Support for more AI coding agents is planned:

• Codex — available via the bundled skill in codex-skill/
• Cursor — coming soon
• Windsurf — coming soon
• Your favorite tool — contributions welcome! See the opencode-commands/ directory for a reference implementation.

Use the Generated CLI Copy Section

Regardless of which platform you used to build it, the generated CLI works the same way:

# Install to PATH
cd gimp/agent-harness && pip install -e .

# Use from anywhere
cli-anything-gimp --help
cli-anything-gimp project new --width 1920 --height 1080 -o poster.json
cli-anything-gimp --json layer add -n "Background" --type solid --color "#1a1a2e"

# Enter interactive REPL
cli-anything-gimp

Each in-repo harness now has a canonical SKILL.md at skills/cli-anything-<software>/SKILL.md, which makes the monorepo directly discoverable via npx skills add HKUDS/CLI-Anything --list. Installed harness packages still ship a compatibility copy at cli_anything/<software>/skills/SKILL.md, and the REPL banner prefers the repo-root canonical file when present, falling back to the packaged copy otherwise.

🤖 Empower Your Agents with CLI-Hub Copy Chapter

CLI-Hub lets agents autonomously discover, install, and use the CLIs they need.

npx skills add HKUDS/CLI-Anything --skill cli-hub-meta-skill -g -y

Also available on: ClawHub, SkillHub, SkillHub.cn

Then prompt:

Find appropriate CLI software in CLI-Hub and complete the task: ...

The meta-skill points agents to the live CLI-Hub catalog, where they can choose a CLI, install it, and read its own SKILL.md for task-specific usage.

💡 CLI-Anything's Vision: Building Agent-Native Software Copy Chapter

• 🌐 Universal Access - Every software becomes instantly agent-controllable through structured CLI.

• 🔗 Seamless Integration - Agents control any application without APIs, GUI, rebuilding or complex wrappers.

• 🚀 Future-Ready Ecosystem - Transform human-designed software into agent-native tools with one command.

🔧 When to Use CLI-Anything Copy Chapter

CLI-Anything's Key Features Copy Chapter

The Agent-Software Gap Copy Section

AI agents are great at reasoning but terrible at using real professional software. Current solutions are fragile UI automation, limited APIs, or dumbed-down reimplementations that miss 90% of functionality.

CLI-Anything's Solution: Transform any professional software into agent-native tools without losing capabilities.

🎯 What Can You Do with CLI-Anything? Copy Chapter

| ### 🛠️ Let Agents Take Your Workflows

Professional or everyday — just throw the codebase at /cli-anything. GIMP, Blender, Shotcut for creative work. LibreOffice, OBS Studio for daily tasks. Don't have the source? Find an open-source alternative and throw that in. You'll instantly get a full CLI your agents can use. | ### 🔗 Unify Scattered APIs into One CLI

Tired of juggling fragmented web service APIs? Feed the docs or SDK manuscripts to /cli-anything and your agents get a powerful, stateful CLI that wraps those individual endpoints into coherent command groups. One tool instead of dozens of raw API calls — stronger capabilities while saving tokens. | ### 🚀 Replace or Supercharge GUI Agents

CLI-Anything can flat-out replace GUI-based agent approaches — no more screenshots, no brittle pixel-clicking. But here's the fun part: once you /cli-anything a GUI software, you can synthesize agent tasks, evaluators, and benchmarks entirely via code and terminal — fully automated, iteratively refinable, massively more efficient. |
| --- | --- | --- |

✨ ⚙️ How CLI-Anything Works Copy Chapter

| ### 🏗️ Fully Automated 7-Phase Pipeline
From codebase analysis to PyPI publishing — the plugin handles architecture design, implementation, test planning, test writing, and documentation completely automatically. | ### 🎯 Authentic Software Integration

Direct calls to real applications for actual rendering. LibreOffice generates PDFs, Blender renders 3D scenes, Audacity processes audio via sox. Zero compromises, Zero toy implementations. |
| --- | --- |
| ### 🔁 Smart Session Management
Persistent project state with undo/redo capabilities, plus unified REPL interface (ReplSkin) that delivers consistent interactive experience across all CLIs. | ### 📦 Zero-Config Installation
Simple pip install -e . puts cli-anything- directly on PATH. Agents discover tools via standard which commands. No setup, no wrappers. |
| ### 🧪 Production-Grade Testing
Multi-layered validation: unit tests with synthetic data, end-to-end tests with real files and software, plus CLI subprocess verification of installed commands. | ### 🐍 Clean Package Architecture
All CLIs organized under cli_anything.* namespace — conflict-free, pip-installable, with consistent naming: cli-anything-gimp, cli-anything-blender, etc. |

🤖 SKILL.md Generation Copy Section

Each generated CLI now has a canonical SKILL.md at skills/cli-anything-<software>/SKILL.md. This makes the current monorepo directly consumable by npx skills, while a packaged compatibility copy at cli_anything/<software>/skills/SKILL.md preserves installed-harness behavior.

What SKILL.md provides:

• YAML frontmatter with name and description for agent skill discovery
• Command groups with all available subcommands documented
• Usage examples for common workflows
• Agent-specific guidance for JSON output, error handling, and programmatic use

SKILL.md files are auto-generated during Phase 6.5 of the pipeline using skill_generator.py, which extracts metadata directly from the CLI's Click decorators, setup.py, and README. The generator now writes the canonical repo-root skill file and refreshes the package-local compatibility copy used by installed harnesses. Inside this repo, the REPL banner points agents to the canonical root skill path; after pip install, it falls back to the packaged copy.

🎬 Real-World Demos Copy Chapter

AI agents using generated CLIs to produce complete, useful artifacts — no GUI needed.

FreeCAD — Curiosity Rover via Preview, Live Preview, and Trajectory Copy Section

Harness: cli-anything-freecad | Preview Stack: preview + preview live + trajectory.json | Artifact: Agent-built Curiosity-style rover

An agent incrementally assembles a Curiosity-inspired rover while publishing real FreeCAD preview bundles, refreshing a live preview session, and recording command-to-preview history for later replay. The resulting demo shows the artifact evolving step by step before the final showcase.

Blender — Orbital Relay Drone via Preview, Live Preview, and Trajectory Copy Section

Harness: cli-anything-blender | Preview Stack: preview + preview live + trajectory.json | Artifact: Agent-built orbital relay drone

An agent uses the Blender harness to grow a hard-surface orbital relay drone under a real preview loop: each stage pushes new render-backed bundles, the live session tracks the current head, and the trajectory ties every command to the matching visual state. The demo finishes with the completed scene ready for a polished turntable.

Draw.io — HTTPS Handshake Diagram Copy Section

Harness: cli-anything-drawio | Time: ~4 min | Artifact: .drawio + .png

An agent creates a full HTTPS connection lifecycle diagram from scratch — TCP three-way handshake, TLS negotiation, encrypted data exchange, and TCP four-way termination — entirely through CLI commands.

Final artifact

Contributed by @zhangxilong-43

Slay the Spire II — Game Automation Copy Section

Harness: cli-anything-slay-the-spire-ii | Artifact: Automated gameplay session

An agent plays through a Slay the Spire II run using the CLI harness — reading game state, selecting cards, choosing paths, and making strategic decisions in real-time.

Contributed by @TianyuFan0504

VideoCaptioner — Auto-Generated Subtitles Copy Section

Harness: cli-anything-videocaptioner | Artifact: Captioned video frames

An agent uses the VideoCaptioner CLI to automatically generate and overlay styled subtitles onto video content, with bilingual text rendering and customizable formatting.

Contributed by @WEIFENG2333

ArcGIS Pro — Live Agent Cartography via the MCP Bridge Copy Section

Harness: arcgis-pro (registered in public_registry.json) | Mode: live-Pro MCP bridge | Artifact: Agent-driven map navigation in a running ArcGIS Pro session

An agent drives a live, open ArcGIS Pro session through an MCP bridge — reading the project, zooming the map to feature layers, running geoprocessing, and exporting layouts — while each step executes inside Pro as you watch. ArcGIS Pro is Esri's commercial GIS desktop (Windows-only, licensed), so this wraps its official ArcPy / ArcGIS Pro SDK rather than being generated from source — the ArcGIS Pro counterpart to the QGIS harness.

Contributed by @Jasper0122

More CLI demos coming soon.

🎬 Demonstrations Copy Chapter

🎯 General-Purpose Copy Section

CLI-Anything works on any software with a codebase — no domain restrictions or architectural limitations.

🏭 Professional-Grade Testing Copy Section

Tested across 18 diverse, complex applications spanning creative, productivity, communication, diagramming, AI image generation, AI content generation, network ad blocking, local LLM inference, native debugging, and graphics profiling domains previously inaccessible to AI agents.

🎨 Diverse Domain Coverage Copy Section

From creative workflows (image editing, 3D modeling, vector graphics) to production tools (audio, office, live streaming, video editing).

✅ Full CLI Generation Copy Section

Each application received complete, production-ready CLI interfaces — not demos, but comprehensive tool access preserving full capabilities.

100% pass rate across all 2,461 tests — 1,732 unit tests + 579 end-to-end tests + 19 Node.js tests.

📊 Test Results Copy Chapter

Each CLI harness undergoes rigorous multi-layered testing to ensure production reliability:

================================ Test Summary ================================
gimp          107 passed  ✅   (64 unit + 43 e2e)
blender       208 passed  ✅   (150 unit + 58 e2e)
inkscape      202 passed  ✅   (148 unit + 54 e2e)
audacity      161 passed  ✅   (107 unit + 54 e2e)
wavetone       30 passed  ✅   (24 unit + 6 default e2e, 2 backend-gated e2e skipped; 32 passed opt-in)
libreoffice   158 passed  ✅   (89 unit + 69 e2e)
mubu           96 passed  ✅   (85 unit + 11 e2e)
obs-studio    153 passed  ✅   (116 unit + 37 e2e)
nslogger      139 passed  ✅   (97 unit + 42 e2e)
kdenlive      155 passed  ✅   (111 unit + 44 e2e)
shotcut       154 passed  ✅   (110 unit + 44 e2e)
zoom           22 passed  ✅   (22 unit + 0 e2e)
drawio        138 passed  ✅   (116 unit + 22 e2e)
eth2-quickstart 18 passed ✅   (18 unit + 3 e2e skipped)
mermaid        10 passed  ✅   (5 unit + 5 e2e)
anygen         50 passed  ✅   (40 unit + 10 e2e)
notebooklm     21 passed  ✅   (21 unit + 0 e2e)
comfyui        73 passed  ✅   (63 unit + 10 e2e)
adguardhome    36 passed  ✅   (24 unit + 12 e2e)
ollama         98 passed  ✅   (87 unit + 11 e2e)
sketch         19 passed  ✅   (19 jest, Node.js)
renderdoc      59 passed  ✅   (45 unit + 14 e2e)
cloudcompare   88 passed  ✅   (49 unit + 39 e2e)
openscreen    101 passed  ✅   (78 unit + 23 e2e)
lldb           27 passed  ✅   (23 unit + 4 e2e)
nsight-graphics 51 passed ✅   (46 unit/CLI + 5 local e2e)
unrealinsights 50 passed  ✅   (49 unit + 1 e2e, 9 backend-gated e2e skipped)
cloudanalyzer  14 passed  ✅   (7 unit + 7 e2e)
3mf            50 passed  ✅   (50 unit)
joplin        134 passed  ✅   (107 unit + 27 e2e, 1 skipped on Windows)
──────────────────────────────────────────────────────────────────────────────
TOTAL        2,464 passed  ✅   100% pass rate

🏗️ CLI-Anything's Architecture Copy Chapter

🎯 Core Design Principles Copy Section

1. Authentic Software Integration — The CLI generates valid project files (ODF, MLT XML, SVG) and delegates to real applications for rendering. We build structured interfaces TO software, not replacements.

2. Flexible Interaction Models — Every CLI operates in dual modes: stateful REPL for interactive agent sessions + subcommand interface for scripting/pipelines. Run bare command → enter REPL mode.

3. Consistent User Experience — All generated CLIs share unified REPL interface (repl_skin.py) with branded banners, styled prompts, command history, progress indicators, and standardized formatting.

4. Agent-Native Design — Built-in --json flag on every command delivers structured data for machine consumption, while human-readable tables serve interactive use. Agents discover capabilities via standard --help and which commands.

5. Zero Compromise Dependencies — Real software is a hard requirement — no fallbacks, no graceful degradation. Tests fail (not skip) when backends are missing, ensuring authentic functionality.

📂 Project Structure Copy Chapter

/* Detailed source-code truncated for AI context efficiency. */

Each agent-harness/ contains an installable Python package under cli_anything.<software>/ with Click CLI, core modules, utils (including repl_skin.py and backend wrapper), and comprehensive tests.

🎯 Plugin Commands Copy Chapter

Examples Copy Section

# Build a complete CLI for GIMP from local source
/cli-anything /home/user/gimp

# Build from a GitHub repo
/cli-anything https://github.com/blender/blender

# Refine an existing harness — broad gap analysis
/cli-anything:refine /home/user/gimp

# Refine with a specific focus area
/cli-anything:refine /home/user/shotcut "vid-in-vid and picture-in-picture compositing"

# Run tests and update TEST.md
/cli-anything:test /home/user/inkscape

# Validate against HARNESS.md standards
/cli-anything:validate /home/user/audacity

🎮 Demo: Using a Generated CLI Copy Chapter

Here's what an agent can do with cli-anything-libreoffice:

# Create a new Writer document
$ cli-anything-libreoffice document new -o report.json --type writer
✓ Created Writer document: report.json

# Add content
$ cli-anything-libreoffice --project report.json writer add-heading -t "Q1 Report" --level 1
✓ Added heading: "Q1 Report"

$ cli-anything-libreoffice --project report.json writer add-table --rows 4 --cols 3
✓ Added 4×3 table

# Export to real PDF via LibreOffice headless
$ cli-anything-libreoffice --project report.json export render output.pdf -p pdf --overwrite
✓ Exported: output.pdf (42,831 bytes) via libreoffice-headless

# JSON mode for agent consumption
$ cli-anything-libreoffice --json document info --project report.json
{
  "name": "Q1 Report",
  "type": "writer",
  "pages": 1,
  "elements": 2,
  "modified": true
}

REPL Mode Copy Section

$ cli-anything-blender
╔══════════════════════════════════════════╗
║       cli-anything-blender v1.0.0       ║
║     Blender CLI for AI Agents           ║
╚══════════════════════════════════════════╝

blender> scene new --name ProductShot
✓ Created scene: ProductShot

blender[ProductShot]> object add-mesh --type cube --location 0 0 1
✓ Added mesh: Cube at (0, 0, 1)

blender[ProductShot]*> render execute --output render.png --engine CYCLES
✓ Rendered: render.png (1920×1080, 2.3 MB) via blender --background

blender[ProductShot]> exit
Goodbye! 👋

📖 The Standard Playbook: HARNESS.md Copy Chapter

HARNESS.md is our definitive SOP for making any software agent-accessible via automated CLI generation.

It encodes proven patterns and methodologies refined through automated generation processes.

The playbook distills key insights from successfully building all 18 diverse, production-ready harnesses.

Critical Lessons Copy Section

See the full methodology: cli-anything-plugin/HARNESS.md

📦 Installation & Usage Copy Chapter

For CLI-Hub Users Copy Section

# Install the package manager
pip install cli-anything-hub

# Browse, search, inspect, and install CLIs
cli-hub list
cli-hub search <query>
cli-hub info <name>
cli-hub install <name>

# Manage installed CLIs
cli-hub update <name>
cli-hub uninstall <name>
cli-hub launch <name> [args...]

For Plugin Users (Claude Code) Copy Section

# Add marketplace & install (recommended)
/plugin marketplace add HKUDS/CLI-Anything
/plugin install cli-anything

# Build a CLI for any software with a codebase
/cli-anything <software-name>

For Generated CLIs Copy Section

# Install any generated CLI
cd <software>/agent-harness
pip install -e .

# Verify
which cli-anything-<software>

# Use
cli-anything-<software> --help
cli-anything-<software>                    # enters REPL
cli-anything-<software> --json <command>   # JSON output for agents

Running Tests Copy Section

# Run tests for a specific CLI
cd <software>/agent-harness
python3 -m pytest cli_anything/<software>/tests/ -v

# Force-installed mode (recommended for validation)
CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<software>/tests/ -v -s

🤝 Contributing Copy Chapter

We welcome contributions! CLI-Anything is designed to be extensible:

• New software targets — Use the plugin to generate a CLI for any software with a codebase, then submit your harness via cli-anything-plugin/PUBLISHING.md.
• Methodology improvements — PRs to HARNESS.md that encode new lessons learned
• Plugin enhancements — New commands, phase improvements, better validation
• Test coverage — More E2E scenarios, edge cases, workflow tests

Limitations Copy Section

• Requires strong foundation models — CLI-Anything relies on frontier-class models (e.g., Claude Opus 4.6, Claude Sonnet 4.6, GPT-5.4) for reliable harness generation. Weaker or smaller models may produce incomplete or incorrect CLIs that require significant manual correction.
• Relies on available source code — The 7-phase pipeline analyzes and generates from source code. When the target software only provides compiled binaries that require decompilation, harness quality and coverage will degrade substantially.
• May require iterative refinement — A single /cli-anything run may not fully cover all capabilities. Running /refine one or more times is often needed to push the CLI's performance and coverage to production quality.

Roadmap Copy Section

• Support for more application categories (CAD, DAW, IDE, EDA, scientific tools)
• Benchmark suite for agent task completion rates
• Community-contributed CLI harnesses for internal/custom software
• Integration with additional agent frameworks beyond Claude Code
• Support packaging APIs for closed-source software and web services into CLIs
• Produce SKILL.md alongside the CLI for agent skill discovery and orchestration

📖 Documentation Copy Chapter

Each generated harness also includes:

• <SOFTWARE>.md — Architecture SOP specific to that application
• tests/TEST.md — Test plan and results documentation

⭐ Star History Copy Chapter

If CLI-Anything helps make your software Agent-native, give us a star! ⭐

📚 Citation Copy Chapter

If you find CLI-Anything useful, please cite our technical report:

@misc{yang2026clianythingagentnativecomputeruse,
      title={CLI-Anything: Towards Agent-Native Computer Use}, 
      author={Yuhao Yang and Tianyu Fan and Chao Huang},
      year={2026},
      eprint={2606.03854},
      archivePrefix={arXiv},
      primaryClass={cs.HC},
      url={https://arxiv.org/abs/2606.03854}, 
}

📄 License Copy Chapter

Apache License 2.0 — free to use, modify, and distribute.

File: adguardhome/agent-harness/cli_anything/adguardhome/README.md Copy Chapter

cli-anything-adguardhome

CLI harness for AdGuardHome - control your ad blocker from the command line or via agents.

Prerequisites Copy Chapter

AdGuardHome must be running. Install:

# Linux - native
curl -s -S -L https://raw.githubusercontent.com/AdguardTeam/AdGuardHome/master/scripts/install.sh | sh -s -- -v

# Docker
docker run --name adguardhome -p 3000:3000 adguard/adguardhome

Installation Copy Chapter

cd agent-harness
pip install -e .
cli-anything-adguardhome --help

Configuration Copy Chapter

export AGH_HOST=localhost
export AGH_PORT=3000
export AGH_USERNAME=admin
export AGH_PASSWORD=secret

# Or save to config file
cli-anything-adguardhome --host localhost --port 3000 --username admin --password secret config save

Usage Copy Chapter

# Interactive REPL (default)
cli-anything-adguardhome

# One-shot commands
cli-anything-adguardhome server status
cli-anything-adguardhome filter list
cli-anything-adguardhome --json stats show

# Filtering
cli-anything-adguardhome filter add --url https://somehost.com/list.txt --name "My List"
cli-anything-adguardhome filter refresh

# DNS rewrites
cli-anything-adguardhome rewrite add --domain "myserver.local" --answer "192.168.1.50"
cli-anything-adguardhome rewrite list

# Clients
cli-anything-adguardhome clients add --name "My PC" --ip 192.168.1.100

# Stats
cli-anything-adguardhome stats show
cli-anything-adguardhome stats reset

Tests Copy Chapter

cd agent-harness
python3 -m pytest cli_anything/adguardhome/tests/test_core.py -v
python3 -m pytest cli_anything/adguardhome/tests/test_full_e2e.py -v -s
CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/adguardhome/tests/ -v -s

File: anygen/agent-harness/cli_anything/anygen/README.md Copy Chapter

AnyGen CLI

A stateful command-line interface for AnyGen OpenAPI — generate professional
slides, documents, websites, diagrams, and more from natural language prompts.
Designed for AI agents and power users.

Prerequisites Copy Chapter

• Python 3.10+
• requests (HTTP client)
• click (CLI framework)
• AnyGen API key (sk-xxx)

Optional (for interactive REPL):

• prompt_toolkit

Install Dependencies Copy Chapter

pip install requests click prompt_toolkit

Get an API Key Copy Chapter

1. Go to anygen.io/home → Setting → Integration
2. Create an API key (format: sk-xxx)
3. Configure it:

# Option 1: Config file (recommended)
cli-anything-anygen config set api_key "sk-xxx"

# Option 2: Environment variable
export ANYGEN_API_KEY="sk-xxx"

How to Run Copy Chapter

All commands are run from the agent-harness/ directory or via the installed command.

One-shot Commands Copy Section

# Show help
cli-anything-anygen --help

# Full workflow: create → poll → download
cli-anything-anygen task run --operation slide --prompt "AI trends presentation" --output ./

# Create a task (returns task ID)
cli-anything-anygen task create --operation doc --prompt "Technical design document"

# Check task status
cli-anything-anygen task status task_xxx

# Poll until completion (with auto-download)
cli-anything-anygen task poll task_xxx --output ./

# Download result file
cli-anything-anygen task download task_xxx --output ./

# JSON output for agent consumption
cli-anything-anygen --json task status task_xxx

Interactive REPL Copy Section

cli-anything-anygen

Inside the REPL, type help for all available commands.

Command Reference Copy Chapter

Task Copy Section

task create --operation <type> --prompt <text> [options]
task run --operation <type> --prompt <text> [--output dir] [options]
task status <task-id>
task poll <task-id> [--output dir]
task download <task-id> --output <dir>
task thumbnail <task-id> --output <dir>
task list [--limit N] [--status completed]
task prepare --message <text> [--file-token tk_xxx] [--save conv.json]

Operations: slide, doc, smart_draw, chat, storybook, data_analysis, website

Create / run options:

• --language / -l — zh-CN or en-US
• --slide-count / -c — Number of slides (slide only)
• --template / -t — Slide template (slide only)
• --ratio / -r — 16:9 or 4:3 (slide only)
• --export-format / -f — pptx/image/thumbnail/docx/drawio/excalidraw
• --file-token — File token from upload (repeatable)
• --style / -s — Style preference

File Copy Section

file upload

Config Copy Section

config set api_key "sk-xxx"
config set default_language "en-US"
config get [key]
config delete <key>
config path

Session Copy Section

session status
session history [--limit N]
session undo
session redo

JSON Mode Copy Chapter

Add --json before the subcommand for machine-readable output:

cli-anything-anygen --json task status task_xxx
cli-anything-anygen --json task list --limit 5

Running Tests Copy Chapter

cd agent-harness

# Unit tests (mock HTTP, no API key needed)
python3 -m pytest cli_anything/anygen/tests/test_core.py -v

# E2E tests (requires ANYGEN_API_KEY)
ANYGEN_API_KEY=sk-xxx python3 -m pytest cli_anything/anygen/tests/test_full_e2e.py -v

# All tests
python3 -m pytest cli_anything/anygen/tests/ -v

Example Workflow Copy Chapter

# Configure API key
cli-anything-anygen config set api_key "sk-xxx"

# Upload a reference file
cli-anything-anygen file upload ./quarterly_data.pdf
# Output: ✓ Uploaded: quarterly_data.pdf → token: tk_abc123

# Requirement analysis (multi-turn)
cli-anything-anygen task prepare --message "I need a quarterly review slide deck" --save conv.json
# AnyGen asks clarifying questions...

cli-anything-anygen task prepare --message "Focus on revenue growth, 10 slides" --input conv.json --save conv.json
# Status: ready, suggested operation: slide

# Create and download in one step
cli-anything-anygen task run \
  --operation slide \
  --prompt "Quarterly business review..." \
  --file-token tk_abc123 \
  --slide-count 10 \
  --style "business formal" \
  --output ./output/

# Or step-by-step
cli-anything-anygen task create --operation slide --prompt "..."
# Task ID: task_xxx

cli-anything-anygen task poll task_xxx --output ./output/
# ✓ Downloaded: ./output/presentation.pptx (2,048,576 bytes)

# Verify the file
cli-anything-anygen --json task status task_xxx

Supported Operations Copy Chapter

File: audacity/agent-harness/cli_anything/audacity/README.md Copy Chapter

Audacity CLI

A stateful command-line interface for audio editing, following the same patterns
as the GIMP and Blender CLIs in this repo.

Architecture Copy Chapter

• JSON project format tracks state (tracks, clips, effects, labels, selection)
• Python stdlib (wave, struct, math) handles WAV I/O and audio processing
• Click provides the CLI framework with subcommand groups and REPL
• Effects are recorded in the project JSON and applied during export/render

Install Copy Chapter

pip install click numpy   # numpy only needed for tests

No other dependencies required. Core functionality uses only Python stdlib.

Run Copy Chapter

# From the agent-harness/ directory:
cd /root/cli-anything/audacity/agent-harness

# One-shot commands
python3 -m cli.audacity_cli project new --name "My Podcast"
python3 -m cli.audacity_cli track add --name "Voice"
python3 -m cli.audacity_cli clip add 0 /path/to/recording.wav
python3 -m cli.audacity_cli effect add normalize --track 0
python3 -m cli.audacity_cli export render output.wav

# JSON output mode (for agent consumption)
python3 -m cli.audacity_cli --json project info

# Interactive REPL
python3 -m cli.audacity_cli repl

Run Tests Copy Chapter

cd /root/cli-anything/audacity/agent-harness

# All tests
python3 -m pytest cli/tests/ -v

# Unit tests only (no real audio files)
python3 -m pytest cli/tests/test_core.py -v

# E2E tests (generates real WAV files)
python3 -m pytest cli/tests/test_full_e2e.py -v

Evaluation (Eval Harness) Copy Chapter

Run a lightweight evaluation suite and generate reports:

# Default output: eval_results/<timestamp>/
python3 -m cli.audacity_cli eval

# Custom output directory
python3 -m cli.audacity_cli eval --out ./eval_out

# Compare to a baseline and fail on regression
python3 -m cli.audacity_cli eval --baseline baseline.json --fail-on-regression

# Update (write) baseline JSON
python3 -m cli.audacity_cli eval --baseline baseline.json --update-baseline

Outputs:

• eval_report.json and eval_report.md
• artifacts/ directory for task outputs

Command Groups Copy Chapter

Example Workflow Copy Chapter

# Create a podcast project
python3 -m cli.audacity_cli project new --name "Episode 1" -o project.json

# Add tracks
python3 -m cli.audacity_cli --project project.json track add --name "Host"
python3 -m cli.audacity_cli --project project.json track add --name "Guest"
python3 -m cli.audacity_cli --project project.json track add --name "Music"

# Import audio clips
python3 -m cli.audacity_cli --project project.json clip add 0 host_recording.wav
python3 -m cli.audacity_cli --project project.json clip add 1 guest_recording.wav --start 0.5
python3 -m cli.audacity_cli --project project.json clip add 2 music.wav --volume 0.3

# Apply effects
python3 -m cli.audacity_cli --project project.json effect add normalize --track 0 -p target_db=-3.0
python3 -m cli.audacity_cli --project project.json effect add compress --track 0 -p threshold=-20 -p ratio=4.0
python3 -m cli.audacity_cli --project project.json effect add fade_in --track 2 -p duration=2.0

# Add labels
python3 -m cli.audacity_cli --project project.json label add 0.0 --text "Intro"
python3 -m cli.audacity_cli --project project.json label add 30.0 -e 60.0 --text "Main discussion"

# Export
python3 -m cli.audacity_cli --project project.json export render episode1.wav --preset wav

File: blender/agent-harness/cli_anything/blender/README.md Copy Chapter

Blender CLI - Agent Harness

A stateful command-line interface for 3D scene editing, following the same
patterns as the GIMP CLI harness. Uses a JSON scene description format
with bpy script generation for actual Blender rendering.

Installation Copy Chapter

# From the agent-harness directory:
pip install click prompt_toolkit

# No Blender installation required for scene editing.
# Blender is only needed if you want to execute the generated render scripts.

Quick Start Copy Chapter

# Create a new scene
python3 -m cli.blender_cli scene new --name "MyScene" -o scene.json

# Add objects
python3 -m cli.blender_cli --project scene.json object add cube --name "Box"
python3 -m cli.blender_cli --project scene.json object add sphere --name "Ball" -l 3,0,1

# Create and assign materials
python3 -m cli.blender_cli --project scene.json material create --name "Red" --color 1,0,0,1
python3 -m cli.blender_cli --project scene.json material assign 0 0

# Add modifiers
python3 -m cli.blender_cli --project scene.json modifier add subdivision_surface -o 0 -p levels=2

# Add camera and light
python3 -m cli.blender_cli --project scene.json camera add -l 7,-6,5 -r 63,0,46 --active
python3 -m cli.blender_cli --project scene.json light add sun -r -45,0,30

# Save
python3 -m cli.blender_cli --project scene.json scene save

# Generate render script
python3 -m cli.blender_cli --project scene.json render execute render.png --overwrite

# Execute with Blender (if installed)
blender --background --python /path/to/_render_script.py

JSON Output Mode Copy Chapter

All commands support --json for machine-readable output:

python3 -m cli.blender_cli --json scene new -o scene.json
python3 -m cli.blender_cli --json --project scene.json object list

Preview and Live Preview Copy Chapter

Blender exposes real preview bundles through the preview command group.

# Capture a real preview bundle
cli-anything-blender --json --project scene.blend-cli.json preview capture --recipe quick

# Query the latest bundle
cli-anything-blender --json --project scene.blend-cli.json preview latest --recipe quick

# Start a poll-mode live preview session
cli-anything-blender --json --project scene.blend-cli.json preview live start --recipe quick --mode poll --source-poll-ms 500

# Query current live-session state
cli-anything-blender --json --project scene.blend-cli.json preview live status --recipe quick

The default quick recipe produces real Blender-rendered hero.png and
workbench.png artifacts. Live sessions persist:

• session.json
• immutable bundle directories
• trajectory.json

Inspect or open published preview state with:

cli-hub previews inspect /path/to/bundle-or-session
cli-hub previews html /path/to/bundle-or-session -o page.html
cli-hub previews watch /path/to/session --open
cli-hub previews open /path/to/bundle-or-session

Interactive REPL Copy Chapter

python3 -m cli.blender_cli repl
# or with existing project:
python3 -m cli.blender_cli repl --project scene.json

Command Groups Copy Chapter

Scene Management Copy Section

scene new      - Create a new scene
scene open     - Open an existing scene file
scene save     - Save the current scene
scene info     - Show scene information
scene profiles - List available scene profiles
scene json     - Print raw scene JSON

Object Management Copy Section

object add       - Add a primitive (cube, sphere, cylinder, cone, plane, torus, monkey, empty)
object remove    - Remove an object by index
object duplicate - Duplicate an object
object transform - Translate, rotate, or scale an object
object set       - Set an object property
object list      - List all objects
object get       - Get detailed object info

Material Management Copy Section

material create - Create a new Principled BSDF material
material assign - Assign a material to an object
material set    - Set a material property
material list   - List all materials
material get    - Get detailed material info

Modifier Management Copy Section

modifier list-available - List all available modifier types
modifier info           - Show modifier details
modifier add            - Add a modifier to an object
modifier remove         - Remove a modifier
modifier set            - Set a modifier parameter
modifier list           - List modifiers on an object

Camera Management Copy Section

camera add        - Add a camera
camera set        - Set a camera property
camera set-active - Set the active camera
camera list       - List all cameras

Light Management Copy Section

light add  - Add a light (point, sun, spot, area)
light set  - Set a light property
light list - List all lights

Animation Copy Section

animation keyframe        - Set a keyframe on an object
animation remove-keyframe - Remove a keyframe
animation frame-range     - Set the animation frame range
animation fps             - Set the FPS
animation list-keyframes  - List keyframes for an object

Render Copy Section

render settings - Configure render settings
render info     - Show current render settings
render presets  - List available render presets
render execute  - Render the scene (generates bpy script)
render script   - Generate bpy script to stdout

Session Copy Section

session status  - Show session status
session undo    - Undo the last operation
session redo    - Redo the last undone operation
session history - Show undo history

Running Tests Copy Chapter

# From the agent-harness directory:

# Run all tests
python3 -m pytest cli/tests/ -v

# Run unit tests only
python3 -m pytest cli/tests/test_core.py -v

# Run E2E tests only
python3 -m pytest cli/tests/test_full_e2e.py -v

# Run with coverage
python3 -m pytest cli/tests/ -v --tb=short

Architecture Copy Chapter

cli/
├── __init__.py
├── __main__.py           # python3 -m cli.blender_cli
├── blender_cli.py        # Main CLI entry point (Click + REPL)
├── core/
│   ├── __init__.py
│   ├── scene.py          # Scene create/open/save/info
│   ├── objects.py        # 3D object management
│   ├── materials.py      # Material management
│   ├── modifiers.py      # Modifier registry + add/remove/set
│   ├── lighting.py       # Camera and light management
│   ├── animation.py      # Keyframe and timeline management
│   ├── render.py         # Render settings and export
│   └── session.py        # Stateful session, undo/redo
├── utils/
│   ├── __init__.py
│   └── bpy_gen.py        # Blender Python script generation
└── tests/
    ├── __init__.py
    ├── test_core.py      # Unit tests (synthetic data, 100+ tests)
    └── test_full_e2e.py  # E2E tests (script gen, roundtrips, workflows)

JSON Scene Format Copy Chapter

The scene is stored as a JSON file with this structure:

{
  "version": "1.0",
  "name": "scene_name",
  "scene": { "fps": 24, "frame_start": 1, "frame_end": 250, ... },
  "render": { "engine": "CYCLES", "resolution_x": 1920, "samples": 128, ... },
  "world": { "background_color": [0.05, 0.05, 0.05], ... },
  "objects": [ { "name": "Cube", "mesh_type": "cube", "location": [0,0,0], ... } ],
  "materials": [ { "name": "Material", "color": [0.8,0.8,0.8,1], ... } ],
  "cameras": [ { "name": "Camera", "focal_length": 50, ... } ],
  "lights": [ { "name": "Light", "type": "POINT", "power": 1000, ... } ],
  "collections": [ { "name": "Collection", "objects": [0, 1] } ],
  "metadata": { "created": "...", "modified": "...", "software": "blender-cli 1.0" }
}

Rendering Copy Chapter

Since Blender's .blend format is binary, this CLI uses a JSON scene format
and generates Blender Python (bpy) scripts for rendering. The workflow:

1. Edit the scene using CLI commands (creates/modifies JSON)
2. Generate a bpy script with render execute or render script
3. Run the script with blender --background --python script.py

The generated scripts reconstruct the entire scene in Blender and render it.

File: browser/agent-harness/cli_anything/browser/README.md Copy Chapter

cli-anything-browser — Browser Automation CLI

A command-line interface for browser automation using DOMShell's MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native browser automation.

Features Copy Chapter

• Filesystem-first navigation: Use ls, cd, cat to explore web pages
• Search: grep for text patterns in the accessibility tree
• Actions: click, type to interact with elements
• JSON output: --json flag for machine-readable output
• Interactive REPL: Stateful session with command history
• Daemon mode: Optional persistent connection for faster interactive use

Installation Copy Chapter

Prerequisites Copy Section

1. Node.js and npx (required for DOMShell MCP server):

   bash Copy

   # Install Node.js from https://nodejs.org/
   node --version
   npx --version

2. Chrome/Chromium with DOMShell extension:

   • Install DOMShell from Chrome Web Store
   • Ensure Chrome is running before using the CLI

3. Python 3.10+:

   bash Copy

   python --version

Install CLI Copy Section

cd browser/agent-harness
pip install -e .

Verify installation:

cli-anything-browser --help

Usage Copy Chapter

One-Shot Commands Copy Section

# Open a page
cli-anything-browser page open https://example.com

# List elements at root
cli-anything-browser fs ls /

# Navigate into a section
cli-anything-browser fs cd /main

# List elements in current directory
cli-anything-browser fs ls

# Read element content
cli-anything-browser fs cat /main/button[0]

# Search for text
cli-anything-browser fs grep "Login"

# Click an element
cli-anything-browser act click /main/button[0]

# Type into an input
cli-anything-browser act type /main/input[0] "Hello, World!"

# Get page info
cli-anything-browser page info

# Navigate back/forward
cli-anything-browser page back
cli-anything-browser page forward

Note: One-shot commands each start with a fresh session (no URL or working directory). For stateful workflows (like cd followed by ls without a path), use the REPL instead.

JSON Output Copy Section

# Get machine-readable output
cli-anything-browser --json fs ls /

# Returns:
{
  "path": "/",
  "entries": [
    {
      "name": "main",
      "role": "landmark",
      "path": "/main"
    }
  ]
}

Daemon Mode (Persistent Connection) Copy Section

For faster interactive use, start daemon mode within a REPL session:

# Start REPL with daemon mode
cli-anything-browser --daemon

# Or start daemon within REPL
session daemon-start

# Run commands (uses persistent connection)
fs ls /
fs cd /main

# Stop daemon when done
session daemon-stop

Note: Daemon mode only works within a single running process (REPL or --daemon flag). State does not persist across separate CLI invocations.

Interactive REPL Copy Section

Run without arguments to enter interactive mode:

cli-anything-browser

REPL commands:

• page open — Open a URL
• fs ls [path] — List elements
• fs cd — Change directory
• fs cat [path] — Read element
• fs grep — Search for text
• fs pwd — Print working directory
• act click — Click element
• act type <text> — Type text
• session status — Show session state
• help — Show commands
• quit — Exit REPL

Command Groups Copy Chapter

`page` — Page Navigation Copy Section

• open — Navigate to URL
• reload — Reload current page
• back — Navigate back in history
• forward — Navigate forward in history
• info — Show current page info

`fs` — Filesystem Commands Copy Section

• ls [path] — List elements at path
• cd — Change directory
• cat [path] — Read element content
• grep [path] — Search for text
• pwd — Print working directory

`act` — Action Commands Copy Section

• click — Click an element
• type <text> — Type text into input

`session` — Session Management Copy Section

• status — Show session status
• daemon-start — Start persistent daemon mode
• daemon-stop — Stop daemon mode

Path Syntax Copy Chapter

DOMShell uses a filesystem-like path syntax for the Accessibility Tree:

/                           — Root (page)
/main                       — Main landmark
/main/div[0]                — First div in main
/main/div[0]/button[2]      — Third button in first div

Array indices are 0-based. Use relative paths with .. to go up.

Examples Copy Chapter

Basic Navigation Copy Section

# Open a page
cli-anything-browser page open https://example.com

# Explore structure
cli-anything-browser fs ls /
cli-anything-browser fs cd /main
cli-anything-browser fs ls

# Go back to root
cli-anything-browser fs cd /

Search and Click Copy Section

# Open page and search for login button
cli-anything-browser page open https://example.com/login
cli-anything-browser fs grep "Login"

# Click the login button (adjust path as needed)
cli-anything-browser act click /main/button[0]

Form Fill Copy Section

# Type into form fields
cli-anything-browser act type /main/input[0] "[email protected]"
cli-anything-browser act type /main/input[1] "password123"

# Click submit
cli-anything-browser act click /main/button[0]

Testing Copy Chapter

Run tests:

# Unit tests (no Chrome required)
pytest cli_anything/browser/tests/test_core.py -v

# E2E tests (requires Chrome + DOMShell)
pytest cli_anything/browser/tests/test_full_e2e.py -v

Troubleshooting Copy Chapter

"npx not found" Copy Section

Install Node.js from https://nodejs.org/

"DOMShell not found" Copy Section

Run: npx @apireno/domshell --version (first run downloads the package)

"DOMShell MCP call failed" Copy Section

• Ensure Chrome is running
• Install DOMShell extension from Chrome Web Store
• Check that DOMShell is enabled in Chrome

Commands hang on first use Copy Section

First npx call downloads DOMShell package (10-50 MB). Subsequent calls are faster. Use --daemon mode for persistent connection.

Architecture Copy Chapter

This CLI follows the CLI-Anything harness methodology:

• Backend: DOMShell MCP server via stdio transport
• State: Page state (URL, working directory, navigation history)
• Pattern: Filesystem-first commands map to Accessibility Tree

Links Copy Chapter

• DOMShell GitHub
• CLI-Anything
• Issue #90

License Copy Chapter

Apache License 2.0 — See CLI-Anything for details.

File: cli-anything-plugin/guides/filter-translation.md Copy Chapter

Filter Translation Pitfalls

When translating effects between formats (e.g., MLT → ffmpeg), watch for these common issues.

Duplicate Filter Types Copy Chapter

Some tools (ffmpeg) don't allow the same filter twice in a chain. If your project has both brightness and saturation filters, and both map to ffmpeg's eq=, you must merge them into a single eq=brightness=X:saturation=Y.

Ordering Constraints Copy Chapter

ffmpeg's concat filter requires interleaved stream ordering:
[v0][a0][v1][a1][v2][a2], NOT grouped [v0][v1][v2][a0][a1][a2].

The error message ("media type mismatch") is cryptic if you don't know this.

Parameter Space Differences Copy Chapter

Effect parameters often use different scales:

• MLT brightness 1.15 = +15%
• ffmpeg eq=brightness=0.06 on a -1..1 scale

Document every mapping explicitly.

Unmappable Effects Copy Chapter

Some effects have no equivalent in the render tool. Handle gracefully (warn, skip) rather than crash.

File: cli-anything-plugin/guides/mcp-backend.md Copy Chapter

MCP Backend Pattern

For services that expose an MCP (Model Context Protocol) server instead of a traditional CLI.

When to Use Copy Chapter

• The software has an official or community MCP server
• No native CLI exists, or MCP provides better functionality
• You want to integrate AI/agent tools that speak MCP protocol

Use case: When the software provides an MCP server instead of a traditional CLI.
Example: DOMShell provides browser automation via MCP tools.

Backend Wrapper (`utils/_backend.py`) Copy Chapter

import asyncio
from typing import Any
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

async def _call_tool(tool_name: str, arguments: dict) -> Any:
    """Call an MCP tool."""
    server_params = StdioServerParameters(
        command="npx",
        args=["@apireno/domshell"]
    )
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            result = await session.call_tool(tool_name, arguments)
            return result

def is_available() -> bool:
    """Check if MCP server is available."""
    # Try to spawn and verify
    ...

# Sync wrappers for each tool
def ls(path: str = "/") -> dict:
    """List directory contents."""
    return asyncio.run(_call_tool("domshell_ls", {"path": path}))

Session Management Copy Chapter

• MCP server spawns per command (stateless from server perspective)
• CLI maintains state (URL, working directory, navigation history)
• Each command re-spawns the MCP server process

Daemon Mode (Optional) Copy Chapter

• Spawn MCP server once, reuse connection for multiple commands
• Reduces latency for interactive use
• Requires explicit start/stop or --daemon flag

Dependencies Copy Chapter

Add mcp>=0.1.0 to install_requires.

Example Implementations Copy Chapter

• browser/agent-harness — DOMShell MCP server for browser automation
• See: https://github.com/HKUDS/CLI-Anything/tree/main/browser/agent-harness

File: cli-anything-plugin/guides/pypi-publishing.md Copy Chapter

PyPI Publishing and Installation (Phase 7)

After building and testing the CLI, make it installable and discoverable.

All cli-anything CLIs use PEP 420 namespace packages under the shared
cli_anything namespace. This allows multiple CLI packages to be installed
side-by-side in the same Python environment without conflicts.

1. Package Structure Copy Chapter

agent-harness/
├── setup.py
└── cli_anything/           # NO __init__.py here (namespace package)
    └── <software>/         # e.g., gimp, blender, audacity
        ├── __init__.py     # HAS __init__.py (regular sub-package)
        ├── <software>_cli.py
        ├── core/
        ├── utils/
        └── tests/

The key rule: cli_anything/ has no __init__.py. Each sub-package
(gimp/, blender/, etc.) does have __init__.py. This is what
enables multiple packages to contribute to the same namespace.

2. setup.py Template Copy Chapter

Create setup.py in the agent-harness/ directory:

from setuptools import setup, find_namespace_packages

setup(
    name="cli-anything-<software>",
    version="1.0.0",
    packages=find_namespace_packages(include=["cli_anything.*"]),
    install_requires=[
        "click>=8.0.0",
        "prompt-toolkit>=3.0.0",
        # Add Python library dependencies here
    ],
    entry_points={
        "console_scripts": [
            "cli-anything-<software>=cli_anything.<software>.<software>_cli:main",
        ],
    },
    python_requires=">=3.10",
)

Important details:

• Use find_namespace_packages, NOT find_packages
• Use include=["cli_anything.*"] to scope discovery
• Entry point format: cli_anything.<software>.<software>_cli:main
• The system package (LibreOffice, Blender, etc.) is a hard dependency
  that cannot be expressed in install_requires. Document it in README.md and
  have the backend module raise a clear error with install instructions:
  python Copy

  # In utils/<software>_backend.py
  def find_<software>():
      path = shutil.which("<software>")
      if path:
          return path
      raise RuntimeError(
          "<Software> is not installed. Install it with:\n"
          "  apt install <software>   # Debian/Ubuntu\n"
          "  brew install <software>  # macOS"
      )

3. Import Convention Copy Chapter

All imports use the cli_anything.<software> prefix:

from cli_anything.gimp.core.project import create_project
from cli_anything.gimp.core.session import Session
from cli_anything.blender.core.scene import create_scene

4. Verification Steps Copy Chapter

Test local installation:

cd /root/cli-anything/<software>/agent-harness
pip install -e .

Verify PATH installation:

which cli-anything-<software>
cli-anything-<software> --help

Run tests against the installed command:

cd /root/cli-anything/<software>/agent-harness
CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<software>/tests/ -v -s

The output must show [_resolve_cli] Using installed command: /path/to/cli-anything-<software>
confirming subprocess tests ran against the real installed binary, not a module fallback.

Verify namespace works across packages (when multiple CLIs installed):

import cli_anything.gimp
import cli_anything.blender
# Both resolve to their respective source directories

Why Namespace Packages Copy Chapter

• Multiple CLIs coexist in the same Python environment without conflicts
• Clean, organized imports under a single cli_anything namespace
• Each CLI is independently installable/uninstallable via pip
• Agents can discover all installed CLIs via cli_anything.*
• Standard Python packaging — no hacks or workarounds

File: cli-anything-plugin/guides/session-locking.md Copy Chapter

Session File Locking

When saving session JSON, use exclusive file locking to prevent concurrent writes from corrupting data.

The Problem Copy Chapter

Never use bare open("w") + json.dump() — open("w") truncates the file before any lock can be acquired.

The Solution: `_locked_save_json` Copy Chapter

Open with "r+", lock, then truncate inside the lock:

def _locked_save_json(path, data, **dump_kwargs) -> None:
    """Atomically write JSON with exclusive file locking."""
    try:
        f = open(path, "r+")            # no truncation on open
    except FileNotFoundError:
        os.makedirs(os.path.dirname(os.path.abspath(path)), exist_ok=True)
        f = open(path, "w")             # first save — file doesn't exist yet
    with f:
        _locked = False
        try:
            import fcntl
            fcntl.flock(f.fileno(), fcntl.LOCK_EX)
            _locked = True
        except (ImportError, OSError):
            pass                        # Windows / unsupported FS — proceed unlocked
        try:
            f.seek(0)
            f.truncate()                # truncate INSIDE the lock
            json.dump(data, f, **dump_kwargs)
            f.flush()
        finally:
            if _locked:
                fcntl.flock(f.fileno(), fcntl.LOCK_UN)

Copy this pattern into core/session.py for all session saves.