Agent skill

Ripgrep

by penpot in penpot/penpot

Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules.

MPL-2.0Auto-check passed

Install Ripgrep

skills CLI
$ npx skills add penpot/penpot --skill ripgrep -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install penpot/penpot ripgrep --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/penpot/penpot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ripgrep .claude/skills/ripgrep && rm -rf skills-src

Use ~/.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/

Facts

Skill name
ripgrep
GitHub stars
61k
Token cost
~788 tokens
SKILL.md length
139 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
MPL-2.0

At a glance

Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules.

  • SKILL.md covers When to use, Quick Start, Advanced Usage and Replacement Operations, plus 5 more sections
  • Calls rg and git

What it does

Ripgrep is an agent skill from penpot/penpot. Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Penpot: The open-source design platform for Product teams that need scalable collaboration. The licence is MPL-2.0.

Example prompts

  • “/ripgrep”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit fc8a126. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Shell commands in SKILL.md call:

    • rg
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ripgrep loads about 788 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 139 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~788

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.

Safety

Auto-check passed

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from penpot/penpot at commit fc8a126, republished under its MPL-2.0 licence (© penpot). 139 words, ~788 tokens.

Download SKILL.mdSave it as .claude/skills/ripgrep/SKILL.md (or your agent's skills folder).
name
ripgrep
description
Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules.
homepage
https://github.com/BurntSushi/ripgrep

ripgrep (rg)

Fast, smart recursive search. Respects .gitignore by default.

When to use

  • Searching file contents across the repo for regex patterns — the default code search, respects .gitignore.

Quick Start

bash
# Search for "TODO" in current directory
rg "TODO"

# Case-insensitive search
rg -i "fixme"

# Search specific file types
rg "error" -t py       # Python files only
rg "function" -t js    # JavaScript files
Common patterns
bash
# Whole word match
rg -w "test"

# Show only filenames
rg -l "pattern"

# Show with context (3 lines before/after)
rg -C 3 "function"

# Count matches
rg -c "import"

Advanced Usage

File type filtering
bash
# Multiple file types
rg "error" -t py -t js

# Exclude file types
rg "TODO" -T md -T txt

# List available types
rg --type-list
Search modifiers
bash
# Regex search
rg "user_\d+"

# Fixed string (no regex)
rg -F "function()"

# Multiline search
rg -U "start.*end"

# Only show matches, not lines
rg -o "https?://[^\s]+"
Path filtering
bash
# Search specific directory
rg "pattern" src/

# Glob patterns
rg "error" -g "*.log"
rg "test" -g "!*.min.js"

# Include hidden files
rg "secret" --hidden

# Search all files (ignore .gitignore)
rg "pattern" --no-ignore

Replacement Operations

bash
# Preview replacements
rg "old_name" --replace "new_name"

# Actually replace (requires extra tool like sd)
rg "old_name" -l | xargs sed -i 's/old_name/new_name/g'

Performance Tips

bash
# Parallel search (auto by default)
rg "pattern" -j 8

# Skip large files
rg "pattern" --max-filesize 10M

# Memory map files
rg "pattern" --mmap

Common Use Cases

Find TODOs in code:

bash
rg "TODO|FIXME|HACK" --type-add 'code:*.{rs,go,py,js,ts}' -t code

Search in specific branches:

bash
git show branch:file | rg "pattern"

Find files containing multiple patterns:

bash
rg "pattern1" | rg "pattern2"

Search with context and color:

bash
rg -C 2 --color always "error" | less -R

Comparison to grep

  • Faster: Typically 5-10x faster than grep
  • Smarter: Respects .gitignore, skips binary files
  • Better defaults: Recursive, colored output, line numbers
  • Easier: Simpler syntax for common tasks

Tips

  • rg is often faster than grep -r
  • Use -t for file type filtering instead of --include
  • Combine with other tools: rg pattern -l | xargs tool
  • Add custom types in ~/.ripgreprc
  • Use --stats to see search performance

Documentation

GitHub: https://github.com/BurntSushi/ripgrep User Guide: https://github.com/BurntSushi/ripgrep/blob/master/GUIDE.md

© penpot, MPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/ripgrep of penpot/penpot.

Open the folder on GitHubat commit fc8a126

Compare with similar skills

Ripgrep 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.

Ripgrep compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ripgrep this skillpenpot/penpot61k—~788Automated safety check: PassMPL-2.0
Searchdavila7/claude-code-templates32k—~339Automated safety check: PassMIT
Algolia Searchdavila7/claude-code-templates32k3 repos~492Automated safety check: PassMIT
Perplexity Web Searchdavila7/claude-code-templates32k12 repos~3.5kAutomated safety check: NotesMIT
X Search via xAIcode-yeongyu/oh-my-openagent70k—~1.4kAutomated safety check: PassCustom licence
Website Searchthedaviddias/Front-End-Checklist74k—~556Automated safety check: PassMIT

Similar skills

  • Search

    davila7/claude-code-templates

    Search Google via Bright Data SERP API. An agent skill from davila7/claude-code-templates.

    32k GitHub stars~339 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Algolia Search

    davila7/claude-code-templates

    Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality.

    32k GitHub starsUsed in 3 repos~492 tokens
    Backend & APIsAuto-check passed
  • Perplexity Web Search

    davila7/claude-code-templates

    Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.

    32k GitHub starsUsed in 12 repos~3.5k tokens
    Research & ScienceAuto-check: notes
  • X Search via xAI

    code-yeongyu/oh-my-openagent

    Rules for using the x_search tool to search X (Twitter) through a connected xAI account: date-bound queries, trusted handles, search operators and split searches.

    70k GitHub stars~1.4k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Website Search

    thedaviddias/Front-End-Checklist

    A skill your agent uses when applies to sites with internal site search functionality.

    74k GitHub stars~556 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Firecrawl Search Integration

    firecrawl/firecrawl

    Guidance for adding Firecrawl's /search endpoint to product code and agent workflows when a feature starts from a query rather than a URL.

    189k GitHub starsUsed in 1 repo~1.1k tokens
    Backend & APIsAuto-check passed

More from penpot/penpot

All 24 skills in this repo
  • Hardens code against vulnerabilities. An agent skill from penpot/penpot.

    61k GitHub starsUsed in 6 repos~4.7k tokens
    Auto-check: notes
  • Create PR

    penpot/penpot

    PR flow — open a new PR for the current task branch (validates base branch, commits, issue and push state) or update an existing PR's title or description to match Penpot conventions.

    61k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Bat Cat

    penpot/penpot

    A cat clone with syntax highlighting, line numbers, and Git integration - a modern replacement for cat.

    61k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed
  • Local CI

    penpot/penpot

    Run local CI-style checks with ./scripts/ci (lint, tests, format) per monorepo module.

    61k GitHub stars~822 tokensUpdated today
    Auto-check passed
  • Ste

    penpot/penpot

    Write or rewrite text in ASD-STE100 Simplified Technical English.

    61k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Code review criteria — the five review axes, core principles, severity format, and verdict for reviewing code changes.

    61k GitHub stars~3.6k tokensUpdated today
    Auto-check passed

Questions about Ripgrep

What does Ripgrep do?

Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules. Ripgrep is an agent skill from penpot/penpot. Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules.

How do I install Ripgrep in Claude Code?

Run `npx skills add penpot/penpot --skill ripgrep -a claude-code`. Or copy the skill folder (.agents/skills/ripgrep in penpot/penpot) into .claude/skills/ripgrep in your project. Claude Code loads it when a task matches its description.

How do I install Ripgrep in Codex?

Run `npx skills add penpot/penpot --skill ripgrep -a codex`. Or copy the skill folder (.agents/skills/ripgrep in penpot/penpot) into .agents/skills/ripgrep in your project. Codex loads it when a task matches its description.

Can I use Ripgrep in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add penpot/penpot --skill ripgrep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ripgrep, .gemini/skills/ripgrep, .github/skills/ripgrep and .opencode/skills/ripgrep in your project.

What does Ripgrep need to run?

Going by SKILL.md and its folder, Ripgrep needs the command-line tools its instructions call (rg and git). Our summary lists: Python 3.

Does Ripgrep access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Ripgrep safe to install?

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. Review the folder before installing.

What licence does Ripgrep use?

Ripgrep is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ripgrep use?

About 788 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ripgrep?

Skills that share tags, products or a category with Ripgrep: Search (davila7/claude-code-templates, 32k stars), Algolia Search (davila7/claude-code-templates, 32k stars), Perplexity Web Search (davila7/claude-code-templates, 32k stars) and X Search via xAI (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ripgrep?

penpot (a GitHub organization) maintains it in penpot/penpot, which has 60,770 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 7, 2026.

Source: penpot/penpot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.