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.
npx agentmods add rules/synaptiai/prompt-decorators/070-workflow-preferencesgit clone --depth 1 https://github.com/synaptiai/prompt-decoratorsWrote 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.
[](https://agentmods.dev/rules/synaptiai/prompt-decorators/070-workflow-preferences)<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>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.
| Model | Per session | Once 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 |
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.
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}
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.
- 6d ago First seen · 68 lines · 464 tokens per session scan A 522433d99ce8
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.
Other cursor rules, from other repositories
react
React, TypeScript, and web development best practices for performance optimization.
session-distill
How to distill a long work session into ContextForge so a fresh session can resume cleanly. Invoke when the user asks to distill/hand off/checkpoint the session, when context is getting bloated and work is unfinished, or before deliberately starting a new session on the same task.
mcp-tools-readme
Keep README in sync when MCP tools change.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.