cli-speed-tools

cli-speed-tools is a skill for Claude Code, Codex from klh/speedy-claude. It costs 42 tokens per session (982 once invoked), scanned A, original, MIT.

A guide to faster command-line tools for listing, searching, finding, viewing, and navigating files. It recommends tools such as ripgrep, fd, bat, and fzf.

In plain words
What is it for?
Listing directories, searching file contents, finding files by name, viewing files, selecting files interactively, stopping processes, and navigating folders.
Why use it?
Slow or hard-to-read terminal commands make codebase work more tedious, especially when searching many files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

Getting it into your agent

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

agentmods
npx agentmods add skills/klh/speedy-claude/cli-speed-tools
Any agent
npx skills add klh/speedy-claude --skill cli-speed-tools
Clone the repo
git clone --depth 1 https://github.com/klh/speedy-claude

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for cli-speed-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/klh/speedy-claude/cli-speed-tools.svg)](https://agentmods.dev/skills/klh/speedy-claude/cli-speed-tools)
Your own site
<a href="https://agentmods.dev/skills/klh/speedy-claude/cli-speed-tools"><img src="https://agentmods.dev/badge/skills/klh/speedy-claude/cli-speed-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 982 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 5.1 $0.00042 $0.00982
Opus 5 $0.00021 $0.00491
Sonnet 5 $0.00008 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured 2d ago against content hash 23012fa3a24d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cli-speed-tools 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills-available/cli-speed-tools/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Speed Tools

Overview

Modern CLI tools provide 10-100x speed improvements over standard utilities while adding useful features like git status, syntax highlighting, and fuzzy search.

Quick Reference

Task Slow (avoid) Fast (use)
List files ls, ls -la eza -la, eza --tree
Search content grep -r, find rg (ripgrep)
Find files find fd
View files cat bat
Fuzzy search fzf
Kill processes kill, pkill fk (fkill)
Dir navigation cd everywhere z (frequency-based)

When to Use

digraph cli_speed {
    "Need to list/search files?" [shape=diamond];
    "Task: list directory" [shape=box];
    "Task: search file contents" [shape=box];
    "Task: find files by name" [shape=box];
    "Task: view file contents" [shape=box];

    "Need to list/search files?" -> "Task: list directory" [label="list"];
    "Need to list/search files?" -> "Task: search file contents" [label="search content"];
    "Need to list/search files?" -> "Task: find files by name" [label="find by name"];
    "Need to list/search files?" -> "Task: view file contents" [label="view"];
}

Core Tools

EZA (Modern ls)

# Detailed list with icons, git status, dirs first
eza -la --icons --git --group-directories-first

# Tree view (2 levels deep)
eza --tree --level=2 --git --icons

Ripgrep (rg)

# Search for pattern in all files
rg "pattern"

# Case-insensitive search with context
rg "pattern" -i -C 2

# Search specific file types
rg "pattern" -t ts -t js

FD (Fast find)

# Find files by name
fd "filename"

# Find by extension
fd "\.ts$"

# Include hidden files
fd "pattern" --hidden

BAT (Enhanced cat)

# View file with syntax highlighting
bat filename.txt

# View specific lines
bat filename.txt -l 10-20

Read the full file on GitHub · 138 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. 2d ago Changed · +6 lines 23012fa3a24d
  2. 6d ago First seen · 132 lines · 42 tokens per session scan A 1b95dc027245

Subscribe to this mod's changes

cli-speed-tools is a skill published in the GitHub repository klh/speedy-claude (11 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 982 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.