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.
git clone --depth 1 https://github.com/theimaginaryfoundation/what-iffWrote 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/theimaginaryfoundation/what-iff/general)<a href="https://agentmods.dev/rules/theimaginaryfoundation/what-iff/general"><img src="https://agentmods.dev/badge/rules/theimaginaryfoundation/what-iff/general/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/theimaginaryfoundation/what-iff/general"><img src="https://agentmods.dev/badge/rules/theimaginaryfoundation/what-iff/general.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02726 | $0.02726 |
| Opus 5 | $0.01363 | $0.01363 |
| Sonnet 5 | $0.00545 | $0.00545 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
general 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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Project Guidelines
Project Overview
This project is a personal assistant AI agent. It's designed to conduct research, help write emails, documents, and other content. It's also designed to be extensible via MCP to support integrations with external services to enable additional agent capabilities.
Project Structure
The project follows standard Go project layout conventions:
cmd/- Main applications for this projectapi-server/- Backend API server for the personal assistant
internal/- Library code that can be used by other applicationsdatastore/- Database access layer using Ent ORMmodels/- Data structures shared across the applicationserver/- Main startup logic for API serverhandlers/- API endpoint handlers for API serverdatabase/- Database connection and configuration utilities
ent/- Auto-generated Ent ORM code for database entities
Development Best Practices
Go Coding Standards
-
Idiomatic Go: Follow the Go proverbs and standard conventions
- Use proper error handling (no panics in production code)
- Embrace interfaces for dependency inversion
- Prefer composition over inheritance
- Use meaningful variable names (
ifor indexes,errfor errors)
-
Code Organization:
- Keep functions small and focused on a single responsibility
- Group related functions in packages with clear boundaries
- Use interfaces to define behavior at package boundaries
- Extract complex logic into well-named helper functions immediately
- Avoid deeply nested loops and conditionals (aim for cyclomatic complexity < 10)
- Use early returns to reduce nesting levels
-
Error Handling:
- Always check errors, never use
_to ignore errors without justification - Return errors rather than using panic
- Use custom error types or error wrapping for context
- Use
fmt.Errorf()with%wfor wrapping errors
- Always check errors, never use
-
Concurrency:
- Use channels and goroutines appropriately
- Always ensure proper goroutine termination
- Use context for cancellation and timeouts
- Use sync primitives (Mutex, WaitGroup) when appropriate
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.
- yesterday First seen · 367 lines · 2,726 tokens per session scan A 4611f0f9bb17
general is a cursor rule published in the GitHub repository theimaginaryfoundation/what-iff (15 stars, last pushed today), licensed Apache-2.0. It adds 2,726 tokens to every session, about $0.0136 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 2026-09-09.
Other cursor rules, from other repositories
python
Python best practices and patterns for modern software development with Flask and SQLite.
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
env-validation-gate
Env validation gate — every app with ≥1 required env var validates its contract at boot via Zod; raw process.env is banned outside the env module. Full pattern in .claude/skills/t2000-env-gate/.