Mirage VFS Adapter Authoring
strukto-ai/mirage
Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.
Adapts the CLI-Anything methodology so Reasonix can build, refine, test and validate a command-line harness for an existing GUI application or source repository.
$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/CLI-Anything cli-anything --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/reasonix-skill .claude/skills/cli-anything && rm -rf skills-srcUse ~/.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/
Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skill into .claude/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", 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 install https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skillType 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.
$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/CLI-Anything cli-anything --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .agents/skills && cp -r skills-src/reasonix-skill .agents/skills/cli-anything && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skill into .agents/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", 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.
$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/CLI-Anything cli-anything --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/reasonix-skill .cursor/skills/cli-anything && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skill into .cursor/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", 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 https://github.com/HKUDS/CLI-Anything.git --path reasonix-skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/CLI-Anything cli-anything --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/reasonix-skill .gemini/skills/cli-anything && rm -rf skills-srcUse ~/.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/
Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skill into .gemini/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", 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.
$ gh skill install HKUDS/CLI-Anything cli-anythingInstalls 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).
$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .github/skills && cp -r skills-src/reasonix-skill .github/skills/cli-anything && rm -rf skills-srcUse ~/.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/
Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skill into .github/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", 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.
$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/CLI-Anything cli-anything --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/reasonix-skill .opencode/skills/cli-anything && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/reasonix-skill into .opencode/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", 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.
cli-anythingAdapts the CLI-Anything methodology so Reasonix can build, refine, test and validate a command-line harness for an existing GUI application or source repository.
Before doing any work, it tries to pull the authoritative methodology from the actual CLI-Anything project: reading a local `HARNESS.md` if the current workspace is that repository or sits next to it, otherwise cloning or downloading the plugin folder from GitHub, and only falling back to a condensed, bundled version of the rules when neither local file nor network access is available.
Input is either a local source path or a GitHub repository URL, with the target software's name derived from its directory name after any needed clone. Reasonix's own built-in tools are mapped onto the harness-building workflow: `bash` for shell commands and tests, `write_file` and `edit_file` for generating and adjusting the Python CLI code, `grep` and `glob` for finding APIs and CLI entry points across the source tree, and an optional CodeGraph pair of tools for deeper symbol and architecture analysis when that integration is enabled.
The generated harness itself stays in a fixed Python format regardless of this adapter, so the Reasonix-specific guidance covers only how the agent gets there, starting with a survey-and-analysis phase before any code is written.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 34f5195. It shows what the files ask for, not the result of running them.
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.
Ships 2 files in scripts/ (PowerShell and Shell), which the agent can run.
Shell commands in SKILL.md call:
pipFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
CLI-Anything for Reasonix loads about 1.8k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 836 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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.
The full file from HKUDS/CLI-Anything at commit 34f5195, republished under its Apache-2.0 licence (© HKUDS). 836 words, ~1,802 tokens.
.claude/skills/cli-anything/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Use this skill when the user wants Reasonix to act like the CLI-Anything builder.
Before implementation, use the full methodology source of truth when available:
CLI-Anything repository, read cli-anything-plugin/HARNESS.md.../cli-anything-plugin/HARNESS.md.cli-anything-plugin from https://github.com/HKUDS/CLI-Anything/tree/main/cli-anything-plugin, then use HARNESS.md and the resources around it from that folder.Accept either:
./gimp or /path/to/softwareDerive the software name from the local directory name after cloning if needed.
Reasonix agents build harnesses by combining these built-in tools:
| Reasonix Tool | Role in Harness Workflow |
|---|---|
bash | Run shell commands, install packages, execute CLI tools, run tests, clone repos |
write_file | Generate Python files (Click CLI, backend modules, tests, setup.py) |
edit_file | Make targeted edits to generated code (single replacement) |
multi_edit | Apply multiple atomic edits to a single file in one pass |
read_file | Read target software source files, existing harness code, test results |
grep | Search for patterns across the target software codebase (APIs, CLI tools, data models) |
glob | Find files matching patterns in the source tree (*.py, *.xml, *.json, etc.) |
ls | List directory contents to understand project structure |
mcp__codegraph__search / mcp__codegraph__context | Optional code graph analysis when CodeGraph is enabled (Reasonix strips the codegraph_ raw prefix, so the model-visible names omit it) |
web_fetch | Fetch documentation, API references, or remote files from the web |
Phase 1 (Analysis) — Use ls + glob to survey the source tree, grep to find API surfaces and CLI entry points, and read_file to inspect key files. When CodeGraph is enabled and its tools are available, use mcp__codegraph__search and mcp__codegraph__context for deeper symbol and architecture analysis.
Phase 2-3 (Design & Implementation) — Use write_file to create new harness files, edit_file / multi_edit to refine generated code, and bash to run pip install -e . for installation.
Phase 4-6 (Testing) — Use bash to run pytest and capture results, read_file to inspect test output, and write_file to update TEST.md.
Phase 7 (Packaging) — Use write_file for setup.py, bash for pip install -e . and which cli-anything-<software> verification.
A full harness build typically requires 25–40 tool-call rounds (architecture inspection, 10+ file writes, installation, and multiple test runs). When invoked via run_skill, the subagent inherits a step budget derived from the parent agent's agent.max_steps setting in reasonix.toml:
max_steps = 0 (the default, meaning unlimited), the subagent also runs with no step cap — this is the recommended configuration for the CLI-Anything workflow.max_steps is set to a finite value, the subagent receives half that budget (minimum 5), which may truncate a complex build before completion.Users who have configured a finite max_steps should ensure it is set to 0 or a sufficiently high value (e.g., 64 or more) before running a CLI-Anything build, so the subagent has enough rounds to complete all seven phases.
Use when the user wants a new harness.
Produce this structure:
<repo-root>/
├── skills/
│ └── cli-anything-<software>/
│ └── SKILL.md
└── <software>/
└── agent-harness/
├── <SOFTWARE>.md
├── setup.py
└── cli_anything/
└── <software>/
├── README.md
├── __init__.py
├── __main__.py
├── <software>_cli.py
├── core/
├── utils/
├── tests/
└── skills/
└── SKILL.mdImplement a stateful Click CLI with:
--json machine-readable outputUse when the harness already exists.
First inventory current commands and tests, then do gap analysis against the target software. Prefer:
Do not remove existing commands unless the user explicitly asks for a breaking change.
Plan tests before writing them. Keep both:
test_core.py for unit coveragetest_full_e2e.py for workflow and backend validationWhen possible, test the installed command via subprocess using cli-anything-<software> rather than only module imports.
Check that the harness:
cli_anything.<software> namespace package layoutsetup.py entry pointSKILL.md filesPrefer the real software backend over reimplementation. Wrap the actual executable or scripting interface in utils/<software>_backend.py when possible. Use synthetic reimplementation only when the project explicitly requires it or no viable native backend exists.
find_namespace_packages(include=["cli_anything.*"])cli_anything/ as a namespace package without a top-level __init__.pycli-anything-<software> through console_scriptscli_anything.<software>/skills/SKILL.md in package dataTEST.md, then tests, then run them.skills/cli-anything-<software>/SKILL.md and cli_anything/<software>/skills/SKILL.md.pip install -e .For an up-to-date list of supported harnesses and their backend patterns, locate registry.json at the CLI-Anything repository root when it is available.
When reporting progress or final results, include:
© HKUDS, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (scripts) in reasonix-skill of HKUDS/CLI-Anything.
Open the folder on GitHubat commit 34f5195
CLI-Anything for Reasonix 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| CLI-Anything for Reasonix this skillHKUDS/CLI-Anything | 52k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Mirage VFS Adapter Authoringstrukto-ai/mirage | 3.7k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| README and DESIGN Generatorfengshao1227/ccg-workflow | 5.9k | — | ~410 | Automated safety check: Notes | MIT | |
| Project Scaffolderpretend1111/claude-desktop-app | 494 | 1 repos | ~498 | Automated safety check: Pass | Custom licence | |
| Light Project StructureLight0305/Light-skills | 641 | — | ~3k | Automated safety check: Notes | MIT | |
| Python Packagingwshobson/agents | 40k | 12 repos | ~911 | Automated safety check: Pass | MIT |
strukto-ai/mirage
Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.
fengshao1227/ccg-workflow
Generates README.md and DESIGN.md skeletons for a module by scanning its structure with a Node script, then lists what to fill in by hand.
pretend1111/claude-desktop-app
Scaffolds a complete, runnable project from scratch, covering web, Python and Node.js projects, with a working entry point and no placeholder code.
Light0305/Light-skills
Audits, scaffolds and safely migrates research project folder structures, keeping existing repositories read-only until you approve exact moves from a plan.
wshobson/agents
Package and publish Python libraries and CLI tools: project layout, pyproject.toml, build backends, wheels and source distributions, versioning and PyPI releases.
hw-native-sys/pypto
Add new operator definitions to PyPTO across all layers (C++, Python IR, Python DSL, tests, codegen, docs).
HKUDS/CLI-Anything
Lets Codex build, refine, test, validate and list CLI-Anything harnesses for GUI applications or source repositories, following the project's full methodology.
HKUDS/CLI-Anything
Guides Hermes Agent through building, refining and testing a CLI-Anything harness that wraps a GUI application or source repository in a scriptable command line.
HKUDS/CLI-Anything
Builds, refines, tests or validates a CLI-Anything harness that wraps a GUI application or source repository as a stateful Click CLI with JSON output and a REPL mode.
HKUDS/CLI-Anything
Drives Krita from the command line to create projects, add layers, apply filters, resize the canvas and export images, with JSON output for agents.
HKUDS/CLI-Anything
Defines, lists, inspects and runs parameterized GUI macros from the command line, with the runtime choosing the execution backend.
HKUDS/CLI-Anything
Capability-based matrix for video production in which the agent picks a provider per capability, from storyboard and sound design to captions, render checks and packaging.
Works with
Categories
Adapts the CLI-Anything methodology so Reasonix can build, refine, test and validate a command-line harness for an existing GUI application or source repository. md` if the current workspace is that repository or sits next to it, otherwise cloning or downloading the plugin folder from GitHub, and only falling back to a condensed, bundled version of the rules when neither local file nor network access is available.
CLI-Anything for Reasonix fits situations like: building a CLI harness for an existing GUI application using Reasonix; adapting a source repository into an agent-friendly command-line interface; testing or validating an already-generated CLI-Anything harness; surveying a codebase's API surface before scaffolding a CLI wrapper.
Run `npx skills add HKUDS/CLI-Anything --skill cli-anything -a claude-code`. Or copy the skill folder (reasonix-skill in HKUDS/CLI-Anything) into .claude/skills/cli-anything in your project. Claude Code loads it when a task matches its description.
Run `npx skills add HKUDS/CLI-Anything --skill cli-anything -a codex`. Or copy the skill folder (reasonix-skill in HKUDS/CLI-Anything) into .agents/skills/cli-anything in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/CLI-Anything --skill cli-anything -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cli-anything, .gemini/skills/cli-anything, .github/skills/cli-anything and .opencode/skills/cli-anything in your project.
Going by SKILL.md and its folder, CLI-Anything for Reasonix needs PowerShell and a shell for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Reasonix; Python; Network access or a local CLI-Anything checkout for the methodology source.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. 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.
CLI-Anything for Reasonix is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with CLI-Anything for Reasonix: Mirage VFS Adapter Authoring (strukto-ai/mirage, 3.7k stars), README and DESIGN Generator (fengshao1227/ccg-workflow, 5.9k stars), Project Scaffolder (pretend1111/claude-desktop-app, 494 stars) and Light Project Structure (Light0305/Light-skills, 641 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
HKUDS (a GitHub organization) maintains it in HKUDS/CLI-Anything, which has 51,696 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on September 22, 2026.
Source: HKUDS/CLI-Anything on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.