guardrails

A set of always-on rules for an AI coding agent's security and behaviour.

In plain words
What is it for?
Applying shared security and behaviour rules across all agents and tasks.
Why use it?
It gives every agent the same baseline instructions, helping keep its actions within the project's expected boundaries.

Cursor rule for Cursor

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 rules/erniker/understudy/guardrails
Clone the repo
git clone --depth 1 https://github.com/erniker/understudy

Made for: Cursor.

Per session 48 This file is loaded in full into every session.
When invoked 48 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 $0.00048 $0.00048
Opus 5 $0.00024 $0.00024
Sonnet 5 $0.00010 $0.00010
Haiku 4.5 $0.00005 $0.00005

Measured yesterday against content hash 95edd5aad9b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guardrails 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 yesterday.

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.

templates/.cursor/rules/guardrails.mdc · 10 lines

What it actually says

{{GUARDRAILS_SECTION}}

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. yesterday First seen · 10 lines · 48 tokens per session scan A 95edd5aad9b2

Subscribe to this mod's changes

guardrails is a cursor rule published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session, about $0.0002 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 2026-08-31.

Related

Other cursor rules, from other repositories

code-optimization

Guidelines for optimizing duplicate and poorly structured code.

leshchenko1979/fast-mcp-telegram · 0 tokens

implementation-workflow

Required plan-first workflow for any implementation request (steps 1–5).

leshchenko1979/fast-mcp-telegram · 1,721 tokens

memory-bank

You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…

leshchenko1979/fast-mcp-telegram · 1,623 tokens

nauro-context

Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…

Nauro-AI/nauro · 272 tokens

language-agnostic-patterns

Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.

madebyaris/advance-minimax-m3-cursor-rules · 37 tokens

cursor-tools-mastery

Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.

madebyaris/advance-minimax-m3-cursor-rules · 36 tokens