ct-rules

A rule set for projects that contain a TODO.md file in their root folder. It defines how CT-numbered tasks should be created, checked, and marked complete.

In plain words
What is it for?
Use it when working on CT-numbered tasks: read TODO.md, update its checkboxes, and mark completed tasks as done.
Why use it?
It keeps task status and acceptance criteria in one project file so progress is recorded consistently.

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/vguleaev/cursor-todo-prompt-kit/ct-rules
Clone the repo
git clone --depth 1 https://github.com/vguleaev/cursor-todo-prompt-kit

Made for: Cursor.

Per session 147 This file is loaded in full into every session.
When invoked 147 The same file — it is already loaded in full.
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 $0.00147 $0.00147
Opus 5 $0.00073 $0.00073
Sonnet 5 $0.00029 $0.00029
Haiku 4.5 $0.00015 $0.00015

Measured 2d ago against content hash 0a53a1bba10c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ct-rules 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/ct-rules.mdc · 13 lines

What it actually says

TODO.md and CT Rules

When a file called TODO.md is present in the project root, you should follow these rules:

  • When you are asked to create or update CT-<number> task, you should use TODO.md file.
  • When you are asked about CT-<number> task, you should check TODO.md file for the task.
  • When you think CT-<number> task is completed, you should mark it as ✅ DONE in TODO.md file.
  • Every acceptance criteria of CT-<number> task that is met should be set to [x] in TODO.md file.
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 · 13 lines · 147 tokens per session scan A 0a53a1bba10c

Subscribe to this mod's changes

ct-rules is a cursor rule published in the GitHub repository vguleaev/cursor-todo-prompt-kit (3 stars, last pushed 6mo ago), licensed MIT. It adds 147 tokens to every session, about $0.0007 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 2026-08-31.