project-rules

project-rules is a cursor rule for Cursor from claude-office-skills/skills. It costs 820 tokens per session, scanned A, original, MIT.

A set of project rules for keeping coding-agent skills and related project files consistent, with English used for code, documentation, names, and configuration.

In plain words
What is it for?
Use it when creating or reviewing SKILL.md files, code comments, variable names, documentation, Git commit messages, and JSON or YAML configuration.
Why use it?
It prevents mixed-language project files and unclear naming or formatting conventions. That makes skills and their supporting code easier for teams to read and maintain.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when creating or reviewing SKILL.md files, code comments, variable names, documentation, Git commit messages, and JSON or YAML configuration.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/claude-office-skills/skills/project-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.

Clone the repo
git clone --depth 1 https://github.com/claude-office-skills/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 project-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/claude-office-skills/skills/project-rules.svg)](https://agentmods.dev/rules/claude-office-skills/skills/project-rules)
Your own site
<a href="https://agentmods.dev/rules/claude-office-skills/skills/project-rules"><img src="https://agentmods.dev/badge/rules/claude-office-skills/skills/project-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 820 This file is loaded in full into every session.
When invoked 820 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 $0.00820 $0.00820
Opus 5 $0.00410 $0.00410
Sonnet 5 $0.00164 $0.00164
Haiku 4.5 $0.00082 $0.00082

Measured 8d ago against content hash afb7ed9f850f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-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 8d 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/project-rules.mdc · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Office Skills - Project Rules

Language Requirements

Code and Documentation Language: English Only

All project artifacts MUST be written in English:

  1. SKILL.md files - All skill names, descriptions, instructions, and examples must be in English
  2. Code comments - All comments in TypeScript, JavaScript, Python must be in English
  3. Variable/function names - Use descriptive English names (camelCase for JS/TS, snake_case for Python)
  4. README and documentation - All markdown documentation in English
  5. Git commit messages - Write commits in English
  6. JSON/YAML keys - Use English keys and values

Example - Correct SKILL.md Header

---
name: contract-review
description: "Analyze contracts for risks, check completeness, and provide recommendations."
category: legal
tags:
  - contract
  - review
  - risk-analysis
---

Example - Incorrect (Do NOT do this)

---
name: 合同审查  # ❌ Chinese name
description: "分析合同风险"  # ❌ Chinese description
---

Skill Design Standards

Frontmatter Structure (YAML)

Every SKILL.md must include:

---
# Basic Information (Required)
name: skill-name-in-kebab-case
description: "Clear English description of what this skill does"
version: "1.0.0"
author: claude-office-skills
license: MIT

# Categorization (Required)
category: legal|hr|finance|sales|marketing|productivity|pdf|document|spreadsheet|presentation|workflow|research|visualization
tags:
  - relevant
  - english
  - tags
department: Target Department

# AI Model Compatibility
models:
  recommended:
    - claude-sonnet-4
    - claude-opus-4
  compatible:
    - claude-3-5-sonnet
    - gpt-4

# MCP Tools Integration (if applicable)
mcp:
  server: office-mcp
  tools:
    - tool_name_1
    - tool_name_2

# Capabilities
capabilities:
  - capability_1
  - capability_2

# Language Support
languages:
  - en
  - zh
---

Content Structure

Skills should follow this structure:

  1. Overview - What the skill does, capabilities and limitations
  2. How to Use - Step-by-step instructions
  3. Domain Knowledge - Embedded expertise, patterns, best practices
  4. Output Format - Expected output structure
  5. Examples - Real-world usage examples
  6. Tips - Best practices for better results
  7. Limitations - Clear boundaries

Read the full file on GitHub · 134 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. 8d ago First seen · 134 lines · 820 tokens per session scan A afb7ed9f850f

Subscribe to this mod's changes

project-rules is a cursor rule published in the GitHub repository claude-office-skills/skills (451 stars, last pushed 7mo ago), licensed MIT. It adds 820 tokens to every session, about $0.0041 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 2026-08-30.