general

general is a cursor rule for Claude Code, Cursor from mordilion/ai-instructions-and-prompts. It costs 1,634 tokens per session, scanned A, original, MIT.

A general set of rules for a project that creates a Claude Code plugin containing reusable AI rules, processes, and prompts.

In plain words
What is it for?
Use it when working anywhere in this plugin repository, including its setup command, validation command, agents, hooks, rules, and configuration.
Why use it?
It gives all work in the project a shared direction and keeps its files modular, clear, maintainable, and efficient for AI assistants.

Cursor rule for Claude CodeCursor

Written for Claude Code and Cursor: SessionStart hook event, but also installed under .cursor/. Also seen: mentions subagents; mentions Claude Code.

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Good fit Use it when working anywhere in this plugin repository, including its setup command, validation command, agents, hooks, rules, and configuration.

Compare 6 cursor rules from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, 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 general

README.md
[![agentmods](https://agentmods.dev/badge/rules/mordilion/ai-instructions-and-prompts/general/github.svg)](https://agentmods.dev/rules/mordilion/ai-instructions-and-prompts/general)
Your own site
<a href="https://agentmods.dev/rules/mordilion/ai-instructions-and-prompts/general"><img src="https://agentmods.dev/badge/rules/mordilion/ai-instructions-and-prompts/general/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 general

Your own site · 80×15
<a href="https://agentmods.dev/rules/mordilion/ai-instructions-and-prompts/general"><img src="https://agentmods.dev/badge/rules/mordilion/ai-instructions-and-prompts/general.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,634 This file is loaded in full into every session.
When invoked 1,634 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 $0.01634 $0.01634
Opus 5 $0.00817 $0.00817
Sonnet 5 $0.00327 $0.00327
Haiku 4.5 $0.00163 $0.00163

Measured 9d ago against content hash 1fb9b7b906e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

general 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 9d 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/general.mdc · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Instructions & Prompts (Claude Code Plugin)

Scope: This applies to ALL tasks. Always active.

Project Nature: This is a meta-project that creates a Claude Code plugin providing AI rules, processes, and prompts for end users.

Project Goals:

  • Users install the plugin and run /ai-iap:setup to configure Claude Code rules for their projects
  • Provide rules and processes as modular Claude Code rules (.claude/rules/**/*.md)
  • All files for rules and processes MUST be token efficient and clear
  • NEVER work with fixed versions. Use user's project-related versions and make it flexible
  • Files MUST follow the same structure for better maintainability

Plugin Structure (this repository; all under plugin/ except marketplace root):

  • plugin/.claude-plugin/plugin.json — Plugin manifest
  • plugin/skills/setup/SKILL.md — Interactive setup wizard (/ai-iap:setup)
  • plugin/skills/validate/SKILL.md — Configuration validator (/ai-iap:validate)
  • plugin/agents/*.md — Built-in agents (code-reviewer, codebase-explorer, test-writer, docs-writer, refactor-helper)
  • plugin/hooks/hooks.json — SessionStart hook for setup hint
  • plugin/lib/config.json — Central configuration (languages, frameworks, structures, processes)
  • plugin/lib/config.schema.json — JSON schema for config validation
  • plugin/lib/claude-subagents.json — Agent templates with rule bindings
  • plugin/lib/rules/ — Rule library (general → language → framework → structure)
  • plugin/lib/processes/ — Process guides (testing, CI/CD, logging, docker, auth, etc.)
  • plugin/lib/code-library/ — Implementation patterns + design patterns

Success Criteria:

  • Consistent code structure and architecture patterns
  • Same security practices applied (OWASP Top 10, input validation, etc.)
  • Same testing approaches (unit, integration, mocking)
  • Same CI/CD best practices (version detection, caching, matrix testing)

CRITICAL RULE - Check Functions BEFORE Generating Code

BEFORE implementing error handling, async operations, input validation, database queries, HTTP requests, or other covered function patterns:

  1. CHECK the functions index — same file, two valid path roots: from this Git repo plugin/lib/code-library/functions/INDEX.md; from the installed plugin directory (CLAUDE_PLUGIN_ROOT, the plugin folder) lib/code-library/functions/INDEX.md
  2. USE the exact pattern from the function file (e.g., error-handling.md)
  3. CHOOSE the appropriate framework version (Plain, Prisma, Laravel, etc.)
  4. COPY the exact code pattern (no installation commands)

Read the full file on GitHub · 123 lines

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. 9d ago First seen · 123 lines · 1,634 tokens per session scan A 1fb9b7b906e7

Subscribe to this mod's changes

general is a cursor rule published in the GitHub repository mordilion/ai-instructions-and-prompts (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,634 tokens to every session, about $0.0082 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.