todo

todo is a cursor rule for Cursor from oleander/home-assistant-mcp-server. It costs 0 tokens per session (391 once invoked), scanned A, original, MIT.

A rule for maintaining a project’s TODO.md file, which is a Markdown checklist of unfinished work.

In plain words
What is it for?
Use it when adding, editing, or organizing TODO items in the MCP Home Assistant Server project. It covers checkbox format, headings, 72-character limits, task breakdown, and dependency order.
Why use it?
It keeps tasks consistently formatted, short, grouped by topic, and ordered so dependent work appears after the work it needs.

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/oleander/home-assistant-mcp-server/todo
Clone the repo
git clone --depth 1 https://github.com/oleander/home-assistant-mcp-server

Made for: Cursor.

Wrote 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.

agentmods badge for todo

README.md
[![agentmods](https://agentmods.dev/badge/rules/oleander/home-assistant-mcp-server/todo.svg)](https://agentmods.dev/rules/oleander/home-assistant-mcp-server/todo)
Your own site
<a href="https://agentmods.dev/rules/oleander/home-assistant-mcp-server/todo"><img src="https://agentmods.dev/badge/rules/oleander/home-assistant-mcp-server/todo.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 391 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 $0.00391
Opus 5 $0.00000 $0.00196
Sonnet 5 $0.00000 $0.00078
Haiku 4.5 $0.00000 $0.00039

Measured 4d ago against content hash e7dba34d0e53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

todo 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 4d 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/todo.mdc · 64 lines

What it actually says

Todo Rule

This rule defines guidelines for working with TODO items in the MCP Home Assistant Server project.

Format Requirements

  • All TODO items should be written in markdown format using checkboxes
  • Each TODO item should be maximum 72 characters long
  • Use - [ ] for incomplete tasks and - [x] for completed tasks
  • Group related tasks under appropriate headers with ## or ### markdown syntax
  • Keep task descriptions concise but clear - summarize the task efficiently
  • Tasks should be ordered by dependency (items that depend on others come later)

Structure

TODO lists should be structured as follows:

# Project Name - TODO List

## Main Category

- [ ] Task 1 description (max 72 chars)
- [ ] Task 2 description (max 72 chars)

### Subcategory

- [ ] More specific task 1
- [ ] More specific task 2

Complexity Guidelines

  • Each task should represent a single unit of work
  • Complex tasks should be broken down into subtasks
  • If a task requires multiple steps, create a subtask list beneath it
  • Avoid overly technical language in task descriptions

Interaction Rules

When working with TODOs:

  1. Always maintain the maximum 72 character limit per task
  2. Keep the hierarchical structure intact
  3. Group similar tasks together under appropriate headers
  4. Mark tasks as complete with - [x] syntax when finished
  5. Do not delete completed tasks (mark them complete instead)
  6. Add new tasks at the appropriate section, not just at the end

Formatting

Use Prettier to maintain consistent formatting:

npx prettier -c -w TODO.md

The todo.mdc rule helps ensure consistent TODO management across the project.

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. 4d ago First seen · 64 lines · 0 tokens per session scan A e7dba34d0e53

Subscribe to this mod's changes

todo is a cursor rule published in the GitHub repository oleander/home-assistant-mcp-server (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 391 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 2026-08-31.