golden-rules

golden-rules is a skill for Claude Code from RealDougEubanks/ClaudeMarketplace. It costs 42 tokens per session (4,330 once invoked), scanned A, original, MIT.

A set of project rules installed in CLAUDE.md, the instruction file Claude Code reads for a project. The rules cover security, coding, naming, design, testing, error handling, API contracts, and performance.

In plain words
What is it for?
Setting always-on project guidance and updating an existing Golden Rules section when a newer version is available.
Why use it?
It keeps the same development standards visible to every Claude Code session instead of relying on people to repeat them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions Claude Code.

Part of the golden-rules plugin — 1 skill shipped together

Good fit Setting always-on project guidance and updating an existing Golden Rules section when a newer version is available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/realdougeubanks/claudemarketplace/golden-rules
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.

Any agent
npx skills add RealDougEubanks/ClaudeMarketplace --skill golden-rules
Clone the repo
git clone --depth 1 https://github.com/RealDougEubanks/ClaudeMarketplace

Made for: Claude Code.

Or install golden-rules, the plugin that ships this one along with the rest of its 1 skill.

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 golden-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/realdougeubanks/claudemarketplace/golden-rules/github.svg)](https://agentmods.dev/skills/realdougeubanks/claudemarketplace/golden-rules)
Your own site
<a href="https://agentmods.dev/skills/realdougeubanks/claudemarketplace/golden-rules"><img src="https://agentmods.dev/badge/skills/realdougeubanks/claudemarketplace/golden-rules/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 golden-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/realdougeubanks/claudemarketplace/golden-rules"><img src="https://agentmods.dev/badge/skills/realdougeubanks/claudemarketplace/golden-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,330 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00042 $0.04330
Opus 5 $0.00021 $0.02165
Sonnet 5 $0.00008 $0.00866
Haiku 4.5 $0.00004 $0.00433

Measured 12d ago against content hash 672715e14bec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

golden-rules 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 12d 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.

skills/golden-rules/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Golden Rules — Always-On Project Standards

Install mandatory security, coding, design, testing, error handling, API contract, and performance standards into this project's CLAUDE.md so they are active for every Claude Code session automatically.

This skill's version: 1.8.0 (also stamped in the marker comment inside the Golden Rules Block below).

Instructions

  1. Use Read to check if ./CLAUDE.md exists in the current working directory.

  2. Use Grep to search ./CLAUDE.md for the string ## Golden Rules (if the file exists).

    • Not found: proceed to step 3 (fresh install).
    • Found, no argument given: check for the version marker comment <!-- golden-rules vX.Y.Z --> inside the section.
      • Marker version equals this skill's version: inform the user the Golden Rules are current and stop.
      • Marker is missing or older: inform the user an older install was found and that /golden-rules --update will replace it with the current version. Stop without modifying anything.
    • Found, --update given: if the marker is missing or older than this skill's version, replace the entire existing ## Golden Rules section (from the ## Golden Rules header up to the next level-2 (##) header, or end of file) with the Golden Rules Block below. If already current, say so and stop.
    • Found, --force given: replace the existing section unconditionally.
  3. If CLAUDE.md does not exist, use Write to create it with the Golden Rules Block below as the full content. If CLAUDE.md exists but lacks the section, use Edit to append the Golden Rules Block to the end of the file.

  4. Confirm to the user what was written (installed fresh, updated from vX.Y.Z, or already current) and that the Golden Rules are now active for every Claude Code session in this project.

Golden Rules Block

Write or append the following content verbatim:


Golden Rules

GOLDEN RULES (MANDATORY — ALL WORK IN THIS PROJECT MUST FOLLOW THESE)

Read the full file on GitHub · 205 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 205 lines · 42 tokens per session scan A 672715e14bec

Subscribe to this mod's changes

golden-rules is a skill published in the GitHub repository RealDougEubanks/ClaudeMarketplace (1 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 4,330 once invoked, 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.