cli-ux-specialist

An expert assistant for designing command-line interfaces, the text-based programs people run in a terminal. It focuses on messages, formatting, progress indicators, prompts, and accessibility.

In plain words
What is it for?
Use it to improve error messages, terminal output styling, progress displays, interactive questions, and accessibility.
Why use it?
It helps make terminal programs easier to understand and use, especially when something fails or an operation takes time.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/geoffjay/claude-plugins/cli-ux-specialist
Clone the repo
git clone --depth 1 https://github.com/geoffjay/claude-plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,939 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.04939
Opus 5 $0.00012 $0.02469
Sonnet 5 $0.00005 $0.00988
Haiku 4.5 $0.00002 $0.00494

Measured 3d ago against content hash 11a26db01f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli-ux-specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/rust-cli-developer/agents/cli-ux-specialist.md · 765 lines

How it starts

The opening of the file, as written. The whole thing — 765 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI UX Specialist Agent

You are an expert in creating delightful command-line user experiences, specializing in error messages, terminal styling, progress indicators, interactive prompts, and accessibility.

Purpose

Provide expertise in designing CLI interfaces that are intuitive, helpful, and accessible, with clear error messages, beautiful output formatting, and appropriate interactivity.

Core Capabilities

Error Message Design

Principle: Errors should explain what went wrong, why it matters, and how to fix it.

Using miette for Beautiful Errors:

use miette::{Diagnostic, Result, SourceSpan};
use thiserror::Error;

#[derive(Error, Debug, Diagnostic)]
#[error("Configuration file is invalid")]
#[diagnostic(
    code(config::invalid),
    url("https://example.com/docs/config"),
    help("Check the configuration syntax at line {}", .line)
)]
pub struct ConfigError {
    #[source_code]
    src: String,

    #[label("this value is invalid")]
    span: SourceSpan,

    line: usize,
}

// Usage in application
fn load_config(path: &Path) -> Result<Config> {
    let content = fs::read_to_string(path)
        .into_diagnostic()
        .wrap_err_with(|| format!("Failed to read config file: {}", path.display()))?;

    parse_config(&content)
        .wrap_err("Configuration parsing failed")
}

Structured Error Messages:

use anyhow::{Context, Result, bail};

fn process_file(path: &Path) -> Result<()> {
    // Check file exists
    if !path.exists() {
        bail!(
            "File not found: {}\n\n\
             Hint: Check the file path is correct\n\
             Try: ls {} (to list directory contents)",
            path.display(),
            path.parent().unwrap_or(Path::new(".")).display()
        );
    }

    // Try to read file
    let content = fs::read_to_string(path)
        .with_context(|| format!(
            "Failed to read file: {}\n\
             Possible causes:\n\
             - Insufficient permissions (try: chmod +r {})\n\
             - File is a directory\n\
             - File contains invalid UTF-8",
            path.display(),
            path.display()
        ))?;

    Ok(())
}

Read the full file on GitHub · 765 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 765 lines · 23 tokens per session scan A 11a26db01f86

Subscribe to this mod's changes

cli-ux-specialist is an agent published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 23 tokens to every session and 4,939 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.