Borrowing it
Nothing to install: this file belongs to elis132/everything-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elis132/everything-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/elis132/everything-mcpWrote 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.
[](https://agentmods.dev/instructions/elis132/everything-mcp/claude-md)<a href="https://agentmods.dev/instructions/elis132/everything-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/elis132/everything-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00527 | $0.00527 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
everything-mcp CLAUDE.md 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 7d 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.
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.
Everything MCP - Developer Guide
Overview
MCP server for voidtools Everything file search. Provides 5 tools for AI agents to search files at lightning speed via Everything's real-time NTFS index.
Project Structure
src/everything_mcp/
├── __init__.py # Package init, version, main() entry
├── __main__.py # python -m everything_mcp
├── py.typed # PEP 561 type checking marker
├── server.py # MCP server, tool definitions (the main file)
├── backend.py # Everything communication via es.exe
└── config.py # Auto-detection of Everything installation
tests/
├── conftest.py # Shared fixtures
├── test_backend.py # Backend + query builders + parsing
├── test_config.py # Auto-detection logic
└── test_server.py # Tool functions + output formatting
Key Design Decisions
- es.exe CLI (not SDK DLL) - maximum compatibility across versions
- No metadata flags (
-size -dm -dc) - clean path-per-line output +os.stat()enrichment is simpler and more reliable than parsing version-dependent columnar output - 5 tools (not 1, not 16) - balanced for AI agent efficiency
- All tools read-only + idempotent - annotated for MCP clients
- Every tool wrapped in try/except - returns error strings, never raw exceptions
- Async subprocess - non-blocking for MCP server event loop
from __future__ import annotations- full PEP 604 union syntax on Python 3.10+
Running
pip install -e ".[dev]"
everything-mcp
Testing
pytest # all tests
pytest -v # verbose
pytest tests/test_backend.py # single module
pytest -x # stop on first failure
Linting
ruff check src/ tests/
ruff format src/ tests/
Adding a New Tool
- Define a Pydantic input model in
server.py(withConfigDict) - Add
@mcp.tooldecorator with MCP annotations - Implement async function using
_get_backend() - Wrap body in
try/except, return error strings on failure - Add tests in
tests/test_server.py - Document in
README.md
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.
- 7d ago First seen · 67 lines · 527 tokens per session scan A 7db8ec0dddda
everything-mcp CLAUDE.md is an instructions file published in the GitHub repository elis132/everything-mcp (19 stars, last pushed 1mo ago), licensed MIT. It adds 527 tokens to every session, about $0.0026 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.