cursor-workflow-rules

Project rules for an AI coding workflow covering planning, focused edits, verification, documentation, and Git practices. Git is a system for tracking code changes.

In plain words
What is it for?
Guiding an agent from understanding a task through implementation and checks, while preserving unrelated edits and avoiding unsafe Git operations.
Why use it?
They help keep changes small, testable, documented, and limited to the requested work.

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/preshan/grocerylist/cursor-workflow-rules
Clone the repo
git clone --depth 1 https://github.com/preshan/GroceryList

Made for: Cursor.

Per session 242 This file is loaded in full into every session.
When invoked 242 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 $0.00242 $0.00242
Opus 5 $0.00121 $0.00121
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured yesterday against content hash 14d5f62ee31f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-workflow-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 yesterday.

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-workflow-rules.mdc · 38 lines

What it actually says

Cursor Workflow Rules

Work sequence

  1. Understand requirement and identify impacted files.
  2. Implement smallest correct change first.
  3. Verify with build/tests/lint for touched scope.
  4. Summarize what changed and what remains.

Editing guidelines

  • Keep changes scoped to the requested task.
  • Do not rewrite unrelated code.
  • Preserve user-authored changes when present.
  • Add brief comments only where logic is non-obvious.

Quality checks

  • Run lint/checks after substantive edits.
  • Prefer fixing root causes over suppressing warnings.
  • Verify offline-critical flows when touching data or session logic.

Documentation discipline

  • Update relevant docs in docs/ when scope/architecture/flow changes.
  • Keep implementation aligned with SRS and compliance documents.

Git hygiene

  • Make atomic commits when asked to commit.
  • Use clear commit messages focused on why.
  • Avoid destructive git operations unless explicitly requested.

Product guardrail reminder

  • Do not introduce cloud-only dependencies for core functionality.
  • Maintain fast, accessible, and low-friction shopping flows.
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. yesterday First seen · 38 lines · 242 tokens per session scan A 14d5f62ee31f

Subscribe to this mod's changes

cursor-workflow-rules is a cursor rule published in the GitHub repository preshan/GroceryList (2 stars, last pushed 3mo ago), licensed MIT. It adds 242 tokens to every session, about $0.0012 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.