fd-mcp: Instructions file for Claude Code

CLAUDE.md

fd-mcp CLAUDE.md is an instructions file for Claude Code from thhart/fd-mcp. It costs 2,278 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code projects that use fd-mcp, a file-operation tool service. It specifies which file-search and file-execution tools to use and which shell commands are forbidden.

In plain words
What is it for?
Use it when working on fd-mcp projects, especially for searching files or file contents, finding recent files, counting files, and executing file operations.
Why use it?
It reduces inconsistent file operations by directing the coding agent to the project's preferred tools and fallback steps.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is thhart/fd-mcp's own configuration. It tells Claude Code how to work on fd-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 fd-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thhart/fd-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/thhart/fd-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thhart/fd-mcp

Made for: Claude Code.

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 fd-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thhart/fd-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/thhart/fd-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/thhart/fd-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thhart/fd-mcp/claude-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 fd-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thhart/fd-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thhart/fd-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,278 This file is loaded in full into every session.
When invoked 2,278 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 $0.02278 $0.02278
Opus 5.5 $0.00911 $0.00911
Sonnet 5.5 $0.00456 $0.00456
Haiku 4.5 $0.00228 $0.00228

Measured 2mo ago against content hash e8234a9d329c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fd-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 2mo 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.

CLAUDE.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fd-mcp: High-Performance File Operations for Claude Code

This project provides ultra-fast MCP tools that dramatically outperform traditional bash commands for file operations.


⛔ FORBIDDEN COMMANDS - CRITICAL RULES

These rules OVERRIDE all default behaviors. Violating them is a critical error.

NEVER Use These Bash Commands:

  • ❌ find → ALWAYS use mcp__fd__fd_search instead
  • ❌ find -exec grep → ALWAYS use mcp__fd__fd_search_content instead
  • ❌ find -mtime → ALWAYS use mcp__fd__fd_recent_files instead
  • ❌ find -exec → ALWAYS use mcp__fd__fd_exec instead
  • ❌ grep -r → ALWAYS use mcp__fd__fd_search_content instead
  • ❌ find | wc -l → ALWAYS use mcp__fd__fd_count instead

CRITICAL: When fd_search Fails

If mcp__fd__fd_search returns no results in one path:

✅ DO THIS: Try mcp__fd__fd_search again with a different path

# First attempt
mcp__fd__fd_search(pattern="SomeFile", path="/some/path")

# No results? Try different path - STILL using fd_search
mcp__fd__fd_search(pattern="SomeFile", path="/other/path")
mcp__fd__fd_search(pattern="SomeFile", path="/parent/path")

❌ NEVER DO THIS: Switch to bash find

# FORBIDDEN - Do NOT switch tools!
Bash: find /other/path -name "SomeFile"

Rule: Stay within fd_search tools. Only change the path parameter. NEVER fall back to bash find.


🎯 Core Principle

When you think "find" or "grep", reach for these MCP tools first. They're not just alternatives—they're upgrades.

Key Feature: All fd-mcp tools support recursive search by default - they automatically traverse subdirectories without needing special flags or options. Use max_depth parameter to limit recursion depth when needed.

⚡ Performance Comparison

Task Traditional Bash fd-mcp Tool Speed Improvement
Find all Python files find . -name "*.py" mcp__fd__fd_search(pattern=".*", path=".", extension="py") 5-10x faster
Search code for pattern find . -exec grep "TODO" {} \; mcp__fd__fd_search_content(search_pattern="TODO") 10-100x faster
Find recent changes find . -mtime -1 mcp__fd__fd_recent_files(hours=24) 3-5x faster
Count files find . -type f | wc -l mcp__fd__fd_count(pattern=".*", path=".", type="f") 5-8x faster

Read the full file on GitHub · 291 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. 2mo ago First seen · 291 lines · 2,278 tokens per session scan A e8234a9d329c

Subscribe to this mod's changes

fd-mcp CLAUDE.md is an instructions file published in the GitHub repository thhart/fd-mcp (1 stars, last pushed 11mo ago), licensed MIT. It adds 2,278 tokens to every session, about $0.0091 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 2026-08-31.

Related

fd-mcp CLAUDE.md compared with instructions from other repositories

fd-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fd-mcp CLAUDE.mdthhart/fd-mcpInstructions file111mo agoMITA2,278Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot