documentation_standards.mouse

A documentation rule set called the Mouse Protocol for recording tasks, plans, execution history, and final results.

In plain words
What is it for?
Keeping task files and plan files accurate, including objectives, deliverables, history logs, execution records, and final summaries.
Why use it?
It prevents important work details from being lost and makes changes easier to understand, maintain, and hand over.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/marv1nnnnn/mouse/documentation_standards.mouse
Clone the repo
git clone --depth 1 https://github.com/marv1nnnnn/mouse

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01626
Opus 5 $0.00000 $0.00813
Sonnet 5 $0.00000 $0.00325
Haiku 4.5 $0.00000 $0.00163

Measured 2d ago against content hash dd1d983d7856, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation_standards.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 2d 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/standards/documentation_standards.mouse.mdc · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.


4. Standards & Quality Assurance: Documentation Standards (Mouse Protocol)

Rationale: Ensures that all work performed and systems developed/modified by the Agent are adequately, accurately, and clearly documented at multiple levels. High-quality documentation is essential for User understanding, future maintainability, collaboration, onboarding, and overall project success. The Agent treats documentation as an integral part of task completion.

4.3 Documentation Standards (Agent's Direct Responsibility)

  • A. Task-Level Documentation (Implicit via Protocol Adherence & Explicit Summaries):
    • Implicit & Foundational: The primary, detailed documentation for the work undertaken is inherently captured by strict adherence to the Mouse Protocol:
      • The Task object (<TaskID>.md): Description, Deliverables, HistoryLog.
      • The PlanFile (<TaskID>_plan.md for M/L/X tasks): Detailed SubTask.Objective, SubTask.InitialKeySteps, SubTask.ProactiveAnalysis, granular SubTask.ExecutionLog, and structured SubTask.FinalOutputSummary (JSON).
    • The Agent MUST ensure all these protocol-defined artifacts are accurate, comprehensive, and reflect the work performed precisely.
    • Explicit Summaries (If Required): If a Task.Deliverable or SubTask.Deliverable explicitly calls for a specific summary document, report, or presentation (e.g., "Generate a Markdown summary of findings for TaskID"), the Agent must produce this as a distinct artifact, linking to more detailed logs where appropriate.
  • B. Code-Level Documentation (Inline Comments & API Documentation - Mandatory):
    • B1. Inline Comments (Clarity for Complex Logic): Agent MUST generate clear, concise inline comments within the code to explain:
      • Complex or non-obvious algorithm sections.
      • Important design decisions or trade-offs made within a function/method.
      • Workarounds for known issues or external system quirks (e.g., // API X returns inconsistent nulls, handling defensively.).
      • TODO:, FIXME:, HACK: annotations with clear explanations and, if possible, a reference to a TaskID for follow-up.
    • B2. API/Function/Class Documentation (Docstrings - Non-Negotiable for Public/Reusable Code):
      • For ALL new or significantly modified public/exported functions, methods, classes, interfaces, and modules, the Agent MUST generate standard API documentation using the idiomatic style for the language (e.g., JSDoc/TSDoc, Python Docstrings with Sphinx/Google/NumPy style, JavaDoc, GoDoc, Doxygen, Swift Markup, KDoc).
      • This documentation MUST minimally include:
        1. A concise summary of the component's purpose and primary responsibility.
        2. Detailed description of each parameter: name, type, purpose, optional/required, default value if any.
        3. Detailed description of the return value: type, purpose, structure if complex.
        4. Any exceptions/errors explicitly thrown or specific error conditions the caller should be aware of.
        5. Usage examples where they significantly aid understanding (especially for complex APIs or utility functions).
        6. Notes on thread safety, immutability, or other non-functional characteristics if relevant.
    • Logging: The generation or significant update of code-level documentation MUST be logged in the relevant SubTask.ExecutionLog (e.g., "Generated Python docstrings for all public methods in data_processor.py.").
  • C. Project-Level Documentation (User Guides, READMEs, Architectural Docs, Changelogs - As Required):
    • If a task introduces new user-facing features, public APIs, significant architectural changes, new operational procedures, or breaking changes, the Agent MUST create or update relevant Bdocumentation. This is mandatory IF:
      • Explicitly specified as a Deliverable in the Task or a SubTask.

Read the full file on GitHub · 56 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. 2d ago First seen · 56 lines · 1,626 tokens per session scan A dd1d983d7856

Subscribe to this mod's changes

documentation_standards.mouse is a cursor rule published in the GitHub repository marv1nnnnn/mouse (14 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,626 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.