xiigen-project-rules-first

xiigen-project-rules-first is a cursor rule for Cursor from lubochka/xiigen-general-skills. It costs 213 tokens per session, scanned A, original, Apache-2.0.

A startup rule that tells an AI coding agent to find and read a project's own guidance before taking meaningful action. Project guidance can include files such as AGENTS.md, CLAUDE.md, or a README.

In plain words
What is it for?
Use it before editing files, running commands, or adapting skills so the agent can record and follow the relevant project constraints.
Why use it?
It helps prevent applying assumptions from memory or from another repository when local naming, safety, testing, or review rules differ.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it before editing files, running commands, or adapting skills so the agent can record and follow the relevant project constraints.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/lubochka/xiigen-general-skills/xiigen-project-rules-first
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.

Clone the repo
git clone --depth 1 https://github.com/lubochka/xiigen-general-skills

Made for: Cursor.

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 xiigen-project-rules-first

README.md
[![agentmods](https://agentmods.dev/badge/rules/lubochka/xiigen-general-skills/xiigen-project-rules-first/github.svg)](https://agentmods.dev/rules/lubochka/xiigen-general-skills/xiigen-project-rules-first)
Your own site
<a href="https://agentmods.dev/rules/lubochka/xiigen-general-skills/xiigen-project-rules-first"><img src="https://agentmods.dev/badge/rules/lubochka/xiigen-general-skills/xiigen-project-rules-first/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for xiigen-project-rules-first

Your own site · 80×15
<a href="https://agentmods.dev/rules/lubochka/xiigen-general-skills/xiigen-project-rules-first"><img src="https://agentmods.dev/badge/rules/lubochka/xiigen-general-skills/xiigen-project-rules-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 213 This file is loaded in full into every session.
When invoked 213 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00213 $0.00213
Opus 5 $0.00106 $0.00106
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured 10d ago against content hash 9fb648c5a3ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xiigen-project-rules-first 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 10d 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.

cursor/rules/xiigen-project-rules-first.mdc · 35 lines

What it actually says

Project Rules First

Purpose

Ensure project-specific rules are read before meaningful action.

When to Use

Use at task startup, before editing files, running commands, or adapting skills.

Inputs

Project rule files such as AGENTS.md, CLAUDE.md, README, docs index, and local skill indexes.

Steps

  1. Locate project entry rules.
  2. Extract mandatory constraints.
  3. Apply only relevant rules to the current task.
  4. Record blockers when rules cannot be found.

Gates

Project rules are either applied or explicitly marked missing.

Evidence

Task outputs follow repository naming, safety, testing, and review constraints.

Anti-Patterns

Starting from memory; treating another repository's AGENTS.md as universal.

authority-chain, stale-baseline-guard

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. 10d ago First seen · 35 lines · 213 tokens per session scan A 9fb648c5a3ce

Subscribe to this mod's changes

xiigen-project-rules-first is a cursor rule published in the GitHub repository lubochka/xiigen-general-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 213 tokens to every session, about $0.0011 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.