todoist-ai: Cursor rule for Cursor

.cursorrules

cursorrules is a cursor rule for Cursor from Service-Ai-LLC/todoist-ai. It costs 223 tokens per session, scanned A, a copy of cursorrules, MIT.

A set of coding rules for a Todoist AI MCP server, including requirements for tool schemas, tests, and documentation. A tool schema describes the inputs an agent is allowed to send.

In plain words
What is it for?
It guides changes to Todoist AI tool parameters, including optional fields, removal values, tests, type checks, builds, and usage documentation.
Why use it?
It prevents a schema pattern that causes the Google Gemini API to fail and sets conventions for clearing fields and checking changes.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Cursor.

This is Service-Ai-LLC/todoist-ai's own configuration. It tells Cursor how to work on todoist-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything todoist-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Service-Ai-LLC/todoist-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Service-Ai-LLC/todoist-ai/main/.cursorrules
Clone the repo
git clone --depth 1 https://github.com/Service-Ai-LLC/todoist-ai

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 cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/service-ai-llc/todoist-ai/cursorrules.svg)](https://agentmods.dev/rules/service-ai-llc/todoist-ai/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/service-ai-llc/todoist-ai/cursorrules"><img src="https://agentmods.dev/badge/rules/service-ai-llc/todoist-ai/cursorrules.svg" alt="Measured on agentmods" height="20"></a>
Per session 223 This file is loaded in full into every session.
When invoked 223 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00223 $0.00223
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured 5d ago against content hash e60db0c8926a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cursorrules 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 5d 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.

Origin

This is a copy

100% identical to cursorrules — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursorrules · 38 lines

What it actually says

Todoist AI MCP Server - Cursor Rules

Critical: Tool Schema Compatibility

NEVER use .nullable() in tool schemas

  • Google Gemini API fails with nullable types in OpenAPI 3.1 format
  • Use .optional() only for optional string fields
  • See PR #181 for reference

Pattern for clearing optional fields:

// ❌ WRONG - breaks Gemini
fieldName: z.string().nullable().optional()

// ✅ CORRECT
fieldName: z.string().optional()

// Runtime handling for clearing:
if (fieldValue === null || fieldValue === 'remove') {
    updateArgs = { ...updateArgs, fieldName: null }
}

Use special strings for removal:

  • Use "unassign" for assignments
  • Use "remove" for other clearable fields
  • Document in schema descriptions

Testing Requirements

  • Add tests for new parameters
  • All 333+ tests must pass
  • Verify build and type-check

Documentation

  • Update schema descriptions
  • Update src/mcp-server.ts guidelines
  • Add usage examples
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. 5d ago First seen · 38 lines · 223 tokens per session scan A e60db0c8926a

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository Service-Ai-LLC/todoist-ai (0 stars, last pushed 23d ago), licensed MIT. It adds 223 tokens to every session, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursorrules, differing in 0 lines, and is treated as a copy.