agent-rules file-system.instructions.md

Security rules for Node.js code that reads, writes, or deletes files and works with file paths. They explain how to build paths safely and prevent path traversal, where input escapes the intended directory.

In plain words
What is it for?
Use them when implementing file uploads, downloads, file serving, directory access, or other Node.js file-system operations.
Why use it?
They reduce the risk of users or external data accessing or changing files outside the allowed location. They also promote consistent handling of encoded and normalized paths.

Instructions file for GitHub Copilot

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.

agentmods
npx agentmods add instructions/lirantal/agent-rules/file-system
Clone the repo
git clone --depth 1 https://github.com/lirantal/agent-rules

Made for: GitHub Copilot.

Per session 433 This file is loaded in full into every session.
When invoked 433 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00433 $0.00433
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00043 $0.00043

Measured 2d ago against content hash 6521bdbfd6a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-rules file-system.instructions.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 2d 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.

.github/instructions/file-system.instructions.md · 25 lines

What it actually says

Paths, Files and File System operations security guidelines

Your Mission

As an agent, you are an expert in secure coding practices for file system operations in Node.js. Your mission is to assist developers in creating secure and reliable code in tasks that involve handling file paths and file system operations. You must prioritize security, prevent vulnerabilities such as path traversal, and provide actionable, detailed guidance.

These rules apply any time you are working on code that involves the following type of operations and Node.js core APIs:

  • fs module operations (e.g., reading, writing, deleting files)
  • path module operations (e.g., joining, normalizing paths)

Securely Constructing File Paths

  • You always construct paths using the following 5 steps:
    1. Base Directory: Define a base directory that is the root directory where you want to operate on files.
    2. Decode The Path: Paths may be provided via a URL and so you should always decode the path using decodeURIComponent() to ensure that any encoded characters like %2e%2e%2f are properly converted to their original form ../.
    3. Normalize The Path: Use path.normalize() to clean up the path and remove any redundant segments like . or ... This helps to prevent path traversal vulnerabilities.
    4. Path Construction: Use path.join() or path.resolve()
    5. Path Validation: Ensure that the resulting path does not escape the base directory by checking that it starts with the base directory.
  • When constructing file paths, never concatenate user input directly into the path. Instead, use the path.join() or path.resolve() methods from the Node.js path module to safely construct file paths.
  • When using path.join() or path.resolve(), you must protect against path traversal attacks by ensuring that the resulting path does not escape the intended directory. You can do this by checking that the resulting path starts with the intended base directory.
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. 2d ago First seen · 25 lines · 433 tokens per session scan A 6521bdbfd6a6

Subscribe to this mod's changes

agent-rules file-system.instructions.md is an instructions file published in the GitHub repository lirantal/agent-rules (62 stars, last pushed 15d ago), licensed Apache-2.0. It adds 433 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories

backend-pro-max-skill CLAUDE.md

Instructions for shashankswe2020-ux/backend-pro-max-skill, covering claude.md, project overview, search command, useful flags and domains.

shashankswe2020-ux/backend-pro-max-skill · 1,506 tokens

skill-bill AGENTS.md

AGENTS.md instructions for oila-gmbh/skill-bill, covering agents.md, project context, product intent, taxonomy and source and generated files.

oila-gmbh/skill-bill · 2,285 tokens

skill-bill CLAUDE.md

Claude Code instructions for oila-gmbh/skill-bill, a project described as: SkillBill packages your engineering judgment into governed skills, then uses a durable Kotlin runtime to ensure agents actually execute that process consistently, resumably, and with bounded context.

oila-gmbh/skill-bill · 3 tokens

agentrq AGENTS.md

Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).

agentrq/agentrq · 826 tokens

thinkrail AGENTS.md

Instructions for JetBrains/thinkrail, covering thinkrail, module structure & boundaries (top-priority requirement), engine: pi only, in-process, architecture (three rings) and repo layout.

JetBrains/thinkrail · 4,503 tokens

claude-code-tresor CLAUDE.md

Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.

alirezarezvani/claude-code-tresor · 5,338 tokens