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.
npx agentmods add instructions/lirantal/agent-rules/file-systemgit clone --depth 1 https://github.com/lirantal/agent-rulesWhat 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 | $0.00433 | $0.00433 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00043 | $0.00043 |
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.
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:
fsmodule operations (e.g., reading, writing, deleting files)pathmodule operations (e.g., joining, normalizing paths)
Securely Constructing File Paths
- You always construct paths using the following 5 steps:
- Base Directory: Define a base directory that is the root directory where you want to operate on files.
- 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%2fare properly converted to their original form../. - 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. - Path Construction: Use
path.join()orpath.resolve() - 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()orpath.resolve()methods from the Node.jspathmodule to safely construct file paths. - When using
path.join()orpath.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.
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.
- 2d ago First seen · 25 lines · 433 tokens per session scan A 6521bdbfd6a6
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.
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.
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.
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.
agentrq AGENTS.md
Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).
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.
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.