agentmods.dev

everything-mcp: Instructions file for Claude Code

AGENTS.md

everything-mcp AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from danielsimonjr/everything-mcp. It costs 975 tokens per session, scanned A, original, MIT.

A repository guide for AI agents working on everything-mcp, a Windows server that searches files through Everything, a desktop file-search tool. It explains the source and built bundle that must stay synchronized.

In plain words
What is it for?
Use it when changing the search or file-information tools, updating the bundle or checking how the server is launched.
Why use it?
It prevents fixes from being made only in the source while the running configuration still uses an unchanged bundle or separate copy.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is danielsimonjr/everything-mcp's own configuration. It tells Claude Code, Codex and OpenCode how to work on everything-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything everything-mcp configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 14repo changed 1mo ago A scan 975 tokens original MIT
View source ↗ danielsimonjr/everything-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to danielsimonjr/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.

Copy the file
curl -O https://raw.githubusercontent.com/danielsimonjr/everything-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/danielsimonjr/everything-mcp

Made for: Claude Code, Codex, OpenCode.

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-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danielsimonjr/everything-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/danielsimonjr/everything-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/danielsimonjr/everything-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/danielsimonjr/everything-mcp/agents-md/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-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/danielsimonjr/everything-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/danielsimonjr/everything-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 975 This file is loaded in full into every session.
When invoked 975 The same file — it is already loaded in full.
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 $0.00975 $0.00975
Opus 5.5 $0.00390 $0.00390
Sonnet 5.5 $0.00195 $0.00195
Haiku 4.5 $0.00097 $0.00097

Measured 1mo ago against content hash 4c844768e42f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

everything-mcp AGENTS.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 1mo 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.

AGENTS.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — everything-mcp

How to operate on this repo without breaking it. Read this and MEMORY.md before making changes. Pairs with TODO.md (open work).

What this is

MCP server (@danielsimonjr/everything-mcp, Windows-only) that wraps es.exe — the command-line client for Everything — and exposes two tools: search and get_file_info.

Stack: TypeScript on Bun, MCP SDK v2 (@modelcontextprotocol/server + /core), Zod tool schemas, McpServer.registerTool + serveStdio.

The five things that bite

  1. Source vs plugin bundle — rebuild after source edits.

    • src/*.ts — the source Bun runs in development.
    • plugin/bundle/index.js — the built ESM artifact plugin/.mcp.json launches with node (${CLAUDE_PLUGIN_ROOT}/bundle/index.js). Self-contained so the plugin cache does not need node_modules.
    • Regenerate with bun run build. Do not hand-edit the bundle. The old bundle/index.mjs / CommonJS index.js pair is gone.

  2. The running server is NOT this repo (on the maintainer's machine). Claude Code may load a separate copy under the plugin cache or %USERPROFILE%\servers\src\…. Changes here do not affect the running MCP until redeployed / marketplace-refreshed. See TODO.md.

  3. CRLF churn — normalize to LF before staging. .gitattributes enforces LF, but editors can still flip files. Before staging:

    tr -d '\r' < src/server.ts > src/server.ts.tmp && mv -f src/server.ts.tmp src/server.ts
git diff HEAD --stat -- src/server.ts   # should be tiny

    Confirm a suspected EOL flip with: git diff HEAD --ignore-all-space -- <file> (empty = pure EOL, no real change).

  4. Stage narrowly — never git add -A. Stage only the files you changed (git add src/ plugin/bundle/index.js package.json bun.lock …) and verify with git status --short (first column = staged) before committing. After a build, stage plugin/bundle/index.js with the matching source change.

Read the full file on GitHub · 78 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. 1mo ago Changed · +11 tokens per session 4c844768e42f
  2. 2mo ago Changed · +2 lines · -36 tokens per session cb9463e858f8
  3. 2mo ago First seen · 76 lines · 1,000 tokens per session scan A d5e3e07aba83

Subscribe to this mod's changes

everything-mcp AGENTS.md is an instructions file published in the GitHub repository danielsimonjr/everything-mcp (14 stars, last pushed 24d ago), licensed MIT. It adds 975 tokens to every session, about $0.0039 per session on Opus 5.5. 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.

Productivity
Related

everything-mcp AGENTS.md compared with instructions from other repositories

everything-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
everything-mcp AGENTS.mddanielsimonjr/everything-mcpInstructions file1424d agoMITA975Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode