af-filesystem-mcp: Instructions file for Claude Code

CLAUDE.md

af-filesystem-mcp CLAUDE.md is an instructions file for Claude Code from maniaclab/af-filesystem-mcp. It costs 3,564 tokens per session, scanned A, original, Apache-2.0.

Contributor instructions for af-filesystem-mcp, a read-only server for accessing an AF user's own shared files.

In plain words
What is it for?
Use them when contributing to, reviewing, configuring, or securing the af-filesystem-mcp project.
Why use it?
They explain the server's purpose, security boundaries, project structure, and differences from related data-access services.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maniaclab/af-filesystem-mcp/claude-md.svg)](https://agentmods.dev/instructions/maniaclab/af-filesystem-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/maniaclab/af-filesystem-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maniaclab/af-filesystem-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,564 This file is loaded in full into every session.
When invoked 3,564 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03564 $0.03564
Opus 5 $0.01782 $0.01782
Sonnet 5 $0.00713 $0.00713
Haiku 4.5 $0.00356 $0.00356

Measured 6d ago against content hash 8699c529ff76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

af-filesystem-mcp CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`minting.py` impersonation pattern, adapted from `subprocess.run` to
CLAUDE.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

af-filesystem-mcp — Contributor Guide

MCP server that gives an AF (Analysis Facility) user browse/read access to their own files on the AF's shared NFS home (/home/<unixname>) and Ceph data area (/data/<unixname>) — nothing more. Read-only in v1: there is no write, delete, rename, or command-execution tool anywhere in this package.

Companion backends in the same af-mcp-platform: ami-mcp (AMI metadata) and rucio-mcp (Rucio data management). This repo follows their conventions (tool naming, broker-mode auth, Helm chart shape) wherever they apply, and departs from them explicitly where this backend's job is different — see "How this differs from ami-mcp/rucio-mcp" below.

Origin

Designed in maniaclab/af-mcp-platform#188, which also has the full design rationale and the (rejected) alternative — an off-the-shelf rust-mcp-filesystem server — and why it was rejected: stdio-only (no per-user identity), and a dangling-symlink write-escape via a validate-then-open TOCTOU. This package exists specifically to not have either problem.

Security model

The security boundary is impersonation, not path-string validation. Every filesystem operation for user alice runs in a short-lived helper subprocess that is started running AS alice's real uid/gid (asyncio.create_subprocess_exec(..., user=uid, group=gid)), never inside the long-lived async server process itself (which would mean a process-wide seteuid() racing across concurrently in-flight requests for different users). This means the kernel — and, for the NFS-mounted homes, the NFS server — enforces every permission check against the real identity: even a bug in this server's own path-pinning logic can only let alice reach what alice's real uid could already reach. This mirrors [voms-token-service][voms-token-service]'s minting.py impersonation pattern, adapted from subprocess.run to asyncio.create_subprocess_exec.

Read the full file on GitHub · 280 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. 6d ago First seen · 280 lines · 3,564 tokens per session scan A 8699c529ff76

Subscribe to this mod's changes

af-filesystem-mcp CLAUDE.md is an instructions file published in the GitHub repository maniaclab/af-filesystem-mcp (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 3,564 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens