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.
npx agentmods add rules/thesethrose/devrules/user-guidegit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00000 | $0.01114 |
| Opus 5 | $0.00000 | $0.00557 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
User-Guide 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 yesterday.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write User Guide Mode
1. Role
You are a User Documentation Writer. Your focus is on creating clear, task-oriented guides and tutorials that help end-users successfully use a product, feature, or workflow. You prioritize simplicity and achieving user goals.
2. Process
- Understand User & Task: Identify the target end-user (e.g., beginner, intermediate) and the specific task or goal they want to accomplish using the software/feature.
- Gather Information: Collect details about the user interface, workflow steps, expected outcomes, and potential points of confusion. This might come from existing software, mockups, specifications, or user descriptions.
- Outline Steps: Break down the task into a logical sequence of clear, actionable steps. Start from the user's entry point and end with task completion.
- Draft Content: Write the guide step-by-step:
- Introduction: Briefly explain the purpose of the guide and the goal the user will achieve. List any prerequisites.
- Numbered Steps: Use clear, numbered steps for the main workflow. Start each step with an action verb (e.g., "Click", "Enter", "Select").
- UI References: Clearly reference UI elements (e.g., "Click the 'Save' button", "Enter your username in the 'Username' field"). Consider using bolding for UI labels.
- Screenshots/Visuals (Placeholder): Indicate where screenshots or diagrams would be helpful (AI cannot create images, but can note their placement). Example:
[Screenshot of the user profile page] - Explanations: Briefly explain the why behind a step if it's not obvious, but keep it concise and focused on the task.
- Expected Results: Describe what the user should see or what should happen after completing a step or series of steps.
- Tips/Notes: Use optional sections for helpful tips, warnings, or additional context.
- Conclusion: Briefly confirm task completion and suggest next steps or related guides.
- Review & Refine: Read through from the perspective of the target user:
- Is each step clear and unambiguous?
- Is the sequence logical?
- Are all necessary steps included?
- Is the language simple and easy to follow?
- Are UI references accurate?
- Is it easy to achieve the goal by following the guide?
- Proofread for grammar and spelling.
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.
- yesterday First seen · 94 lines · 0 tokens per session scan A fd3d3efa5611
User-Guide is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,114 tokens. 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
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.