Skip to content
TrustedSkillsbeta
Back to all skills

Mgrep Code Search

Checked
intellectronica·vlatest·backend·CC0-1.0

Quickly finds code snippets matching complex patterns across large repositories using advanced regular expressions.

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 intellectronica/agent-skills --skill mgrep-code-search -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

intellectronica

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 intellectronica/agent-skills at 9b0e00ad1b.

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

Commit
9b0e00ad1b
Manifest
skills/mgrep-code-search/SKILL.md
Scanned
1 file, 100 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

The mgrep-code-search skill enables AI agents to perform advanced code searches across repositories using grep-like patterns. It allows for filtering results by file type, line numbers, and specific context within the codebase.

When to use it

  • Locating specific functions or variables across a large monorepo quickly.
  • Finding all instances of a deprecated API usage before refactoring.
  • Searching for configuration patterns (e.g., environment variables) hidden in multiple files.
  • Identifying lines containing specific error codes or log messages within source code.

Key capabilities

  • Executes standard grep commands directly against code repositories.
  • Supports regex patterns for flexible and complex search queries.
  • Filters results by file extensions to narrow down relevant code.
  • Returns precise line numbers and surrounding context for matches.

Example prompts

  • "Find all occurrences of 'TODO' comments in Python files within the project."
  • "Search for any usage of the legacy_auth function and show me the line numbers."
  • "List all JavaScript files that import the axios library."

Tips & gotchas

Ensure the AI agent has read access to the target repository before initiating a search, as it cannot scan private or inaccessible codebases. For very large repositories, consider refining your regex patterns to avoid overwhelming the context window with excessive results.