Skip to content
TrustedSkillsbeta
Back to all skills

Mgrep

Checked
mixedbread-ai·vlatest·other·Apache-2.0

Mgrep efficiently searches multiple files for specific patterns, saving time and effort in complex data analysis tasks.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add mixedbread-ai/mgrep --skill mgrep -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

mixedbread-ai

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned mixedbread-ai/mgrep at 5c1ba628c6.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
5c1ba628c6
Manifest
plugins/mgrep/skills/mgrep/SKILL.md
Scanned
1 file, 55 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The mgrep skill enables AI agents to perform advanced text searching and pattern matching within codebases or large document sets. It extends standard grep functionality by allowing natural language queries to locate specific lines, files, or contexts efficiently.

When to use it

  • You need to find a specific function definition across a large repository without knowing the exact file path.
  • You want to search for error messages or log patterns scattered throughout multiple configuration files.
  • You are debugging and need to quickly locate all instances of a particular variable usage or regex pattern.

Key capabilities

  • Natural language text searching within code and documents.
  • Pattern matching similar to traditional command-line grep tools.
  • Context-aware retrieval of specific lines based on query descriptions.

Example prompts

  • "Find all occurrences of the calculateTax function in this project."
  • "Search for any log entries containing 'Connection timeout' across the server logs."
  • "Locate lines in the configuration files that define the API endpoint URL."

Tips & gotchas

Ensure your AI agent has access to the relevant file system or document storage before invoking mgrep. Performance may degrade significantly when searching extremely large repositories without indexing.