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/marv1nnnnn/mouse/guiding_software_principles.mousegit clone --depth 1 https://github.com/marv1nnnnn/mouseWhat 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 | $0.03502 | $0.03502 |
| Opus 5 | $0.01751 | $0.01751 |
| Sonnet 5 | $0.00700 | $0.00700 |
| Haiku 4.5 | $0.00350 | $0.00350 |
Grade A, and why
guiding_software_principles.mouse 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 3d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guiding Software Engineering Principles (Agent's Foundational Directives for Mouse Protocol)
Rationale: These principles are fundamental to crafting excellent software and ensuring operational integrity. The Agent is mandated to internalize these principles and actively apply them as primary drivers during all phases of task execution, especially when designing system components, writing or refactoring code, and performing proactive analysis during planning. Any intentional deviations from these principles in generated code MUST be explicitly justified, documented in the
ExecutionLogorProactiveAnalysis, and, if significant, flagged for User awareness.
1. DRY (Don't Repeat Yourself)
Core Tenet: "Every piece of knowledge or logic must have a single, unambiguous, authoritative representation within a system." Rationale: Repetitive code, logic, or data definitions significantly increase maintenance burden, introduce high risks of inconsistency upon modification, lead to code bloat, and make the system harder to reason about.
- Agent's Mandate:
- Proactive Detection & Rigorous Elimination: During code analysis, generation, or modification, actively identify and flag all instances of duplicated or near-duplicated code sections, logic patterns, configuration values, or documentation snippets. Log these findings.
- Prioritize Abstraction: When redundancy is found, the Agent MUST prioritize and (if within scope or approved) implement suitable abstractions. This includes creating well-defined functions, methods, classes, reusable components, constants, configuration parameters, or documentation includes/references to centralize the repeated knowledge.
- Planning for Reuse: When generating a
PlanFile, strategically evaluate if common utilities, services, data structures, or sub-task patterns can fulfill requirements for multiple steps, thereby promoting inherent reuse and reducing overall plan complexity. - Data & Documentation Consistency: If information is repeated across documentation or task definitions, the Agent MUST suggest referencing a single, canonical source of truth or using transclusion mechanisms if available.
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.
- 3d ago First seen · 106 lines · 3,502 tokens per session scan A 04f4b19ec625
guiding_software_principles.mouse is a cursor rule published in the GitHub repository marv1nnnnn/mouse (14 stars, last pushed 1y ago), licensed MIT. It adds 3,502 tokens to every session, about $0.0175 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
engineering-ticket-template-cursorrules-prompt-file
Cursor rules for engineering development with ticket template integration.
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
cypress-integration-testing-cursorrules-prompt-file
Cursor rules for Cypress development with integration testing.
go-backend-scalability-cursorrules-prompt-file
Cursor rules for Go development with backend scalability.
git-conventional-commit-messages
Cursor rules for Git development with conventional commit messages integration.
cloudflare-email-telegram-cursorrules-prompt-file
Cursor rules for setting up email-to-Telegram forwarding via Cloudflare Email Routing and Workers using the mail2tg CLI.