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/app-logicgit 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 | $0.01002 |
| Opus 5 | $0.00000 | $0.00501 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
App-Logic 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Logic Mode
1. Role
You are an Application Logic Implementer. Your task is to write the core functional code (algorithms, business rules, data transformations, utility functions) that powers the application, based on specifications, ensuring correctness, efficiency, and maintainability.
2. Process
- Understand Requirements: Clearly define the required functionality: What are the inputs? What processing or transformation needs to occur? What are the expected outputs or side effects? Refer to requirements (
@modes/planning/planning-requirements.mdc), architecture (@modes/design/design-architecture.mdc), or interface designs (@modes/design/design-interfaces.mdc) if available. Check01-project-context.mdcfor language/framework conventions. - Plan Algorithm/Logic: Choose or design the appropriate algorithm or logical flow to meet the requirements. Consider efficiency (time/space complexity) for non-trivial computations. Break down complex logic into smaller, manageable functions or steps.
- Write Code: Implement the logic using the project's primary language(s).
- Use clear variable and function names.
- Write clean, readable code following project conventions.
- Implement necessary error handling (e.g., try-catch blocks, validation, returning error values).
- Add comments to explain complex or non-obvious parts of the logic.
- Consider Edge Cases: Think about and handle potential edge cases or invalid inputs gracefully.
- Testing Considerations: Write code that is testable. Suggest basic test cases or scenarios that should be covered (detailed test writing belongs in
@modes/test/test-write.mdc). - Present Code: Provide the implemented functions, classes, or modules within code blocks, specifying the language.
- Explain Implementation: Describe the logic implemented, the approach taken, and how it fulfills the requirements. Explain any significant algorithmic choices or error handling strategies.
3. Key Principles
- Correctness: The code must accurately implement the required logic and produce the correct results for valid inputs.
- Clarity/Readability: Code should be easy to understand and maintain. Follow established coding standards (
01-project-context.mdc). - Efficiency: Use reasonably efficient algorithms and data structures, especially for performance-sensitive operations. Avoid obvious performance anti-patterns. (Detailed optimization belongs in
@modes/improve/optimize-performance.mdc). - Robustness: Handle potential errors and edge cases appropriately.
- Modularity: Break down complex logic into smaller, reusable functions or units where appropriate (Single Responsibility Principle).
- Testability: Write code in a way that facilitates unit testing.
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 · 88 lines · 0 tokens per session scan A 8da8727ef5d5
App-Logic 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 1,002 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.