cursor_rules

Guidelines for creating and maintaining Cursor rules, which are instructions that shape how an AI coding assistant works in a project.

In plain words
What is it for?
Use them when managing Cursor rules or completing project subtasks that require documentation, approval pauses, and requirement checks.
Why use it?
They define how subtasks, approvals, documentation, and completion checks should be handled 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/wiggitywhitney/mcp-commit-story/cursor_rules
Clone the repo
git clone --depth 1 https://github.com/wiggitywhitney/mcp-commit-story

Made for: Cursor.

Per session 758 This file is loaded in full into every session.
When invoked 758 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 $0.00758 $0.00758
Opus 5 $0.00379 $0.00379
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 2d ago against content hash 1cf0793b43c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor_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/cursor_rules.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules Structure and Maintenance

Subtask Execution Flow

When working on subtasks:

  • Complete each subtask fully without pausing for approval unless the subtask explicitly contains the phrase "PAUSE FOR MANUAL APPROVAL" or similar explicit instructions to stop and ask for approval
  • Follow appropriate structure based on subtask type (see tdd_requirements.mdc)
  • Pause only between subtasks to confirm the next one to work on
  • When you see phrases like "GET APPROVAL FOR DESIGN CHOICES", "PAUSE FOR MANUAL APPROVAL", or similar explicit instructions to stop, pause and ask for approval on those specific items only
  • Never ask for approval on implementation details that aren't marked for approval

Automatic Documentation and Completion

At the end of each subtask automatically:

  • Add documentation following documentation.mdc standards
  • Do not remove existing information unless it's incorrect
  • Do not ask for approval on documentation changes
  • Double check all subtask requirements are met
  • If all requirements are met, mark the subtask complete
  • Only ask for help if you can't determine whether requirements are met

Explicit Approval Pauses

  • If a subtask plan contains 'PAUSE FOR MANUAL APPROVAL' or similar instructions, always pause and request approval at that step, even if general rules say to proceed.
  • After writing failing tests and a stub, check the subtask plan for required approval points before implementing.
  • Echo the next step and approval checkpoint to the user before proceeding.
  • Summarize required approval points at the start of each subtask.
  • This rule takes precedence over general 'no approval needed' rules.

Rule Structure Guidelines

Required Rule Structure

---
description: Clear, one-line description of what the rule enforces
globs: path/to/files/*.ext, other/path/**/*
alwaysApply: boolean
---

- **Main Points in Bold**
  - Sub-points with details
  - Examples and explanations

Read the full file on GitHub · 84 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 · 84 lines · 758 tokens per session scan A 1cf0793b43c9

Subscribe to this mod's changes

cursor_rules is a cursor rule published in the GitHub repository wiggitywhitney/mcp-commit-story (15 stars, last pushed 1y ago), licensed MIT. It adds 758 tokens to every session, about $0.0038 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.