everything-search

everything-search is a skill for Claude Code from elis132/everything-mcp. It costs 74 tokens per session (713 once invoked), scanned A, original, MIT.

A Windows file-search skill that uses Everything, a local index of files and folders. It can search by name, type, size, location, or recent changes.

In plain words
What is it for?
Finding files and folders, locating recent files, listing files by type, reading basic file details, and counting matching files or their disk usage.
Why use it?
It avoids slow scans through large Windows drives when you need to find files. It also helps check the size of a search before listing many results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the everything-mcp plugin — 1 skill, 1 MCP server shipped together

Good fit Finding files and folders, locating recent files, listing files by type, reading basic file details, and counting matching files or their disk usage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elis132/everything-mcp/everything-search
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.

Any agent
npx skills add elis132/everything-mcp --skill everything-search
Clone the repo
git clone --depth 1 https://github.com/elis132/everything-mcp

Made for: Claude Code.

Or install everything-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 everything-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/elis132/everything-mcp/everything-search/github.svg)](https://agentmods.dev/skills/elis132/everything-mcp/everything-search)
Your own site
<a href="https://agentmods.dev/skills/elis132/everything-mcp/everything-search"><img src="https://agentmods.dev/badge/skills/elis132/everything-mcp/everything-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for everything-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/elis132/everything-mcp/everything-search"><img src="https://agentmods.dev/badge/skills/elis132/everything-mcp/everything-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00074 $0.00713
Opus 5 $0.00037 $0.00357
Sonnet 5 $0.00015 $0.00143
Haiku 4.5 $0.00007 $0.00071

Measured 9d ago against content hash a5e68f26b28a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

everything-search 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 9d 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.

skills/everything-search/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The everything_* MCP tools query voidtools Everything's real-time NTFS index. A search over millions of files returns in milliseconds, so prefer these tools over shell commands (dir /s, Get-ChildItem -Recurse, glob) for ANY filename-based lookup outside the current project directory.

Picking the right tool

Task Tool
Find files/folders by name, extension, size, date everything_search
"What changed in the last hour/day/week?" everything_find_recent
All videos / documents / code / archives somewhere everything_search_by_type
Metadata or first N lines of specific files everything_file_details
"How many?" / "How much disk space?" everything_count_stats

Use everything_count_stats BEFORE listing when a query might match thousands of files - check the scope first, then narrow.

Query syntax essentials

Space between terms = AND. Key operators:

report.pdf                    name contains "report.pdf"
*.py                          extension wildcard
ext:py;js;ts                  multiple extensions
path:C:\Projects ext:py       restrict to a directory tree
size:>10mb  size:1kb..1mb     size filters
dm:today  dm:last1week        modified date
dc:2024                       created date
"exact name.txt"              phrase with spaces (quote it)
a | b                         OR
!node_modules                 exclude
folder:                       folders only
file:                         files only
dupe:                         duplicate names
empty:                        empty folders
regex:^test_.*\.py$           regex (or pass match_regex=true)

Patterns that work well

  • Locate a project someone mentioned: everything_search(query="folder: myproject")
  • Find a config file of unknown location: everything_search(query="wg0.conf | wireguard ext:conf")
  • Recently downloaded file: everything_find_recent(period="1hour", path="C:\\Users\\<user>\\Downloads")
  • Disk usage of build artifacts: everything_count_stats(query="path:C:\\Projects node_modules folder:", include_size=true)
  • Then inspect what you found: everything_file_details(paths=[...], preview_lines=30)

Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 74 tokens per session scan A a5e68f26b28a

Subscribe to this mod's changes

everything-search is a skill published in the GitHub repository elis132/everything-mcp (19 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 713 once invoked, about $0.0004 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.