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.
git clone --depth 1 https://github.com/claude-office-skills/skillsWrote 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.
[](https://agentmods.dev/rules/claude-office-skills/skills/project-rules)<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>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.
| Model | Per session | Once 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 |
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.
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:
- SKILL.md files - All skill names, descriptions, instructions, and examples must be in English
- Code comments - All comments in TypeScript, JavaScript, Python must be in English
- Variable/function names - Use descriptive English names (camelCase for JS/TS, snake_case for Python)
- README and documentation - All markdown documentation in English
- Git commit messages - Write commits in English
- 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:
- Overview - What the skill does, capabilities and limitations
- How to Use - Step-by-step instructions
- Domain Knowledge - Embedded expertise, patterns, best practices
- Output Format - Expected output structure
- Examples - Real-world usage examples
- Tips - Best practices for better results
- Limitations - Clear boundaries
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.
- 8d ago First seen · 134 lines · 820 tokens per session scan A afb7ed9f850f
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.