rules-prompt

Inject code-style, security, and testing rules into Claude's SessionStart context.

1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/JayJihyunKim/rein --skill rules-prompt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rules-prompt
Source: https://github.com/JayJihyunKim/rein/tree/main/plugins/rein-core/skills/rules-prompt
Command: npx skills add https://github.com/JayJihyunKim/rein --skill rules-prompt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude Code deployments require consistent, enforced rules at session start to prevent prompt drift and unsafe prompts. This skill centralizes and enforces three guardrails—code-style, security, and testing—so teams can maintain policy compliance automatically.

Core Features & Use Cases

  • Bundles three prompt-only rules into a single, reusable policy
  • Reads rule content from code-style.md, security.md, and testing.md for easy updates
  • Uses session-start-rules.sh to inject rules into Claude's SessionStart context
  • Supports per-rule overrides via .rein/policy/rules.yaml
  • Helpful for teams aiming to standardize prompt governance in code-focused workflows

Quick Start

Start a Claude Code session and ensure the session-start-rules.sh hook loads the three prompt rules into the SessionStart context.

Frequently Asked Questions about rules-prompt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I inject prompt rules into Claude Code at session start?

To inject prompt rules at session start, use a shell hook that reads markdown policy files and emits them into the SessionStart context. This skill automates that by bundling code-style, security, and testing rules into the initialization workflow.

What is the best way to enforce coding standards and security policies in Claude Code sessions?

Enforcing coding standards and security policies in Claude Code requires centralizing guardrails in markdown files and loading them via a session-start hook. This skill provides a reusable policy bundle to automatically maintain compliance across tasks.

Can I override specific prompt rules for different projects in Claude Code?

Yes, you can override specific prompt rules by configuring a YAML policy file. This skill supports per-rule overrides via a designated rules.yaml file, allowing teams to customize coding standards, security, and testing policies per project.

How do I update the code-style, security, and testing rules applied to my AI agent?

You update prompt rules by editing the respective markdown content files for code-style, security, and testing. The session-start shell hook reads these markdown files directly, so changes apply automatically the next time a Claude Code session initializes.

Does this prompt rule injection approach work without external dependencies?

Yes, this prompt rule injection approach works without external dependencies. It uses a standalone shell script to read markdown files and emit additional context, requiring no additional packages or libraries to enforce policies in the Claude Code environment.