CLI-Anything turns software and services into command-line interfaces that AI agents can use to perform tasks and produce artifacts. It is intended for people building or using agent workflows with tools such as coding assistants, design software, and other applications. The catalogue entries are skills, commands, a plugin, and a rule for working with CLI-Anything.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HKUDS/CLI-Anything --skill cli-anything-macrocligit clone --depth 1 https://github.com/HKUDS/CLI-AnythingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-macrocli)<a href="https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-macrocli"><img src="https://agentmods.dev/badge/skills/hkuds/cli-anything/cli-anything-macrocli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-macrocli"><img src="https://agentmods.dev/badge/skills/hkuds/cli-anything/cli-anything-macrocli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 77 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.01479 |
| Opus 5.5 | $0.00027 | $0.00592 |
| Sonnet 5.5 | $0.00013 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
cli-anything-macrocli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MacroCLI CLI
What It Is
The MacroCLI converts valuable GUI workflows into parameterized, CLI-callable macros. Agents never touch the GUI directly — they call macros through this stable CLI, and the runtime routes execution to the best available backend (native plugin/API, file transformation, semantic UI control, or precompiled GUI macro replay).
Installation
cd macrocli/agent-harness
pip install -e .
Requirements: Python 3.10+, PyYAML, click, prompt-toolkit.
Quick Start (for agents)
# 1. See what macros are available
cli-anything-macrocli macro list --json
# 2. Inspect a macro's parameters
cli-anything-macrocli macro info export_file --json
# 3. Dry-run to check params without side effects
cli-anything-macrocli --dry-run macro run export_file \
--param output=/tmp/test.txt --json
# 4. Execute a macro
cli-anything-macrocli macro run export_file \
--param output=/tmp/result.txt --json
# 5. See what backends are available
cli-anything-macrocli backends --json
Command Reference
Global Flags
| Flag | Description |
|---|---|
--json |
Machine-readable JSON output on stdout |
--dry-run |
Simulate all steps, skip side effects |
--session-id <id> |
Resume or create a named session |
macro group
| Command | Description |
|---|---|
macro list |
List all available macros |
macro info <name> |
Show macro schema (parameters, steps, conditions) |
macro run <name> --param k=v |
Execute a macro |
macro dry-run <name> --param k=v |
Simulate without side effects |
macro validate [name] |
Structural validation |
macro define <name> |
Scaffold a new macro YAML |
session group
| Command | Description |
|---|---|
session status |
Show session statistics |
session history |
Show recent run history |
session save |
Persist session to disk |
session list |
List all saved sessions |
backends
cli-anything-macrocli backends --json
# Shows: native_api, file_transform, semantic_ui, gui_macro, recovery
# and whether each is available in the current environment.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 221 lines · 67 tokens per session scan A d461b37bf7be
cli-anything-macrocli is a skill published in the GitHub repository HKUDS/CLI-Anything (53,491 stars, last pushed 25d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,479 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
agent-browser
Use the agent-browser CLI to exercise web interfaces, inspect rendered accessibility state, verify interactions, and capture screenshots. Use for browser-based UI testing and evidence collection. Do not use as a substitute for deterministic Playwright coverage when an automated regression test is the requested…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.