cursorrules

Repository rules for an AI coding agent that describe how to understand the project, reuse existing code, plan larger changes, and verify results. Tailor is the project-intelligence system named by these rules.

In plain words
What is it for?
Use them before substantial changes to consult the project's constitution and index, search for reusable components and utilities, prefer built-in features, follow the specification workflow, and run targeted tests.
Why use it?
They help the agent follow the repository's decisions and avoid duplicating code or claiming checks passed without evidence. They also provide a consistent process for changes that are more than simple edits.

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/amanktyr/tailor/cursorrules
Clone the repo
git clone --depth 1 https://github.com/AmanKtyr/Tailor

Made for: Cursor.

Per session 190 This file is loaded in full into every session.
When invoked 190 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod 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 $0.00190 $0.00190
Opus 5 $0.00095 $0.00095
Sonnet 5 $0.00038 $0.00038
Haiku 4.5 $0.00019 $0.00019

Measured yesterday against content hash 5fc9965b1ad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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.

Origin

This is a copy

92% identical to tailor — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursorrules · 11 lines

What it actually says

AI Agent Guidance (Powered by Tailor)

This repository uses Tailor for project intelligence, Spec-Driven Development, and Reuse-First engineering discipline.

Core Directives

  1. Constitution & Project Memory First: Always consult .ai/CONSTITUTION.md and .ai/INDEX.md before making non-trivial changes.
  2. Reuse-First Decision Ladder: Always search existing components, hooks, and utilities before writing new code.
  3. Pragmatic Simplicity: Prefer standard library and native platform APIs over trivial external dependencies.
  4. Spec-Driven Discipline: For non-trivial features, follow the specification lifecycle (specs/<id>/spec.md -> plan.md -> tasks.md).
  5. Truthful Verification: Verify changes with targeted tests; never fabricate test passes.
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 · 11 lines · 190 tokens per session scan A 5fc9965b1ad7

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository AmanKtyr/Tailor (3 stars, last pushed 9d ago), licensed MIT. It adds 190 tokens to every session, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to tailor, differing in 5 lines, and is treated as a copy.