070-workflow-preferences

070-workflow-preferences is a cursor rule for Cursor from synaptiai/prompt-decorators. It costs 464 tokens per session, scanned A, original, Apache-2.0.

Workflow rules for making focused software changes while considering tests, side effects, architecture, and compatibility.

In plain words
What is it for?
Implementing features, fixing issues, reviewing changes, writing tests, preserving existing patterns, and recording significant design decisions.
Why use it?
They help prevent unrelated edits and make important changes easier to verify and maintain.

Cursor rule for Cursor

Written for Cursor: installed under .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/synaptiai/prompt-decorators/070-workflow-preferences
Clone the repo
git clone --depth 1 https://github.com/synaptiai/prompt-decorators

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 070-workflow-preferences

README.md
[![agentmods](https://agentmods.dev/badge/rules/synaptiai/prompt-decorators/070-workflow-preferences.svg)](https://agentmods.dev/rules/synaptiai/prompt-decorators/070-workflow-preferences)
Your own site
<a href="https://agentmods.dev/rules/synaptiai/prompt-decorators/070-workflow-preferences"><img src="https://agentmods.dev/badge/rules/synaptiai/prompt-decorators/070-workflow-preferences.svg" alt="Measured on agentmods" height="20"></a>
Per session 464 This file is loaded in full into every session.
When invoked 464 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 5.1 $0.00464 $0.00464
Opus 5 $0.00232 $0.00232
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00046 $0.00046

Measured 6d ago against content hash 522433d99ce8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

070-workflow-preferences 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 6d 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/070-workflow-preferences.mdc · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Workflow Preferences

1.0.0

Context

  • When implementing new features
  • When fixing bugs or addressing issues
  • When refactoring or improving existing code
  • When reviewing code changes

Requirements

  • Focus exclusively on code areas relevant to the current task
  • Do not modify code unrelated to the assigned task
  • Write thorough tests for all major functionality
  • Preserve existing architectural patterns unless explicitly instructed otherwise
  • Analyze potential impacts of changes on other methods and code areas
  • Consider side effects before implementing changes
  • Maintain backward compatibility when possible
  • Document significant architectural decisions

Examples

1. Only modify the relevant validation function

def validate_user_input(user_data): """Validate user registration data with fixed email validation.""" if not is_valid_email(user_data.get('email')): raise ValidationError("Invalid email format") # Other existing validation logic...

2. Add thorough tests for the fix

def test_validate_user_input_with_invalid_email(): """Test that invalid emails are properly rejected.""" with pytest.raises(ValidationError): validate_user_input({'email': 'invalid-email'})

def test_validate_user_input_with_valid_email(): """Test that valid emails pass validation.""" result = validate_user_input({'email': '[email protected]'}) assert result is True

1. Modifying unrelated authentication system

def authenticate_user(username, password): """Authenticate user with new token-based system.""" # Completely rewriting authentication when task was only about validation token = generate_jwt_token(username, password) return {'authenticated': True, 'token': token}

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 464 tokens per session scan A 522433d99ce8

Subscribe to this mod's changes

070-workflow-preferences is a cursor rule published in the GitHub repository synaptiai/prompt-decorators (43 stars, last pushed 3d ago), licensed Apache-2.0. It adds 464 tokens to every session, about $0.0023 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.