80-vibe-coding

A set of rules for quickly building prototypes, proof-of-concepts, hackathon projects, and minimum viable products. It encourages rapid iteration and is intended for exploratory work rather than production-critical systems.

In plain words
What is it for?
Use it for prototypes, early product validation, exploratory development, hackathons, and time-sensitive feature experiments.
Why use it?
It helps developers move past small debugging problems and test product ideas quickly when working code matters more than polish.

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/luxvil/ai-coding-rules/80-vibe-coding
Clone the repo
git clone --depth 1 https://github.com/Luxvil/ai-coding-rules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.01301
Opus 5 $0.00000 $0.00651
Sonnet 5 $0.00000 $0.00260
Haiku 4.5 $0.00000 $0.00130

Measured yesterday against content hash 085a294a99c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

80-vibe-coding 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.

Origin

This is a copy

100% identical to 80-vibe-coding — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/rules/80-vibe-coding.mdc · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎸 Vibe Coding Protocol

"The vibes are the goal. The code is the vehicle." — Vibe Coding Manifesto

When to Activate

Enable Vibe mode for:

  • ✅ Prototyping and proof-of-concept
  • ✅ Exploratory development
  • ✅ Time-critical feature delivery
  • ✅ Hackathons and MVPs
  • ✅ Early-stage product validation

Do NOT use for:

  • ❌ Production-critical systems
  • ❌ Security-sensitive code
  • ❌ Code that others will maintain immediately
  • ❌ Financial or healthcare systems

Core Principles

Traditional Vibe Mode
Debug line by line Reroll with better prompt
Get it right first time Iterate rapidly
Commit when complete Commit every working state
Focus on code quality Focus on product delivery
Perfect is the goal Working is the goal

The Reroll Strategy

When to Reroll (Regenerate)

IF debugging_time > 10 minutes THEN
  → Stop debugging
  → Clarify the problem
  → Regenerate the module with better context

How to Reroll

  1. Identify what's not working
  2. Document the failure mode
  3. Provide clearer context/constraints
  4. Generate fresh implementation
  5. Compare and merge the best parts

This is often faster than fixing convoluted code.


Commit Checkpoint System

Rule: Every Working State = Commit

# ✅ Good commit frequency in Vibe mode
git commit -m "feat: basic form renders"
git commit -m "feat: form validates on submit"
git commit -m "feat: form submits to API"
git commit -m "fix: handle empty state"
git commit -m "feat: success toast on submit"

Why?

  • Easy rollback to last working state
  • Clear progress visibility
  • Safe experimentation

Commit Message Format

type: short description

# Types:
feat:     New feature
fix:      Bug fix
wip:      Work in progress (Vibe mode)
refactor: Code improvement
style:    Formatting only

Speed Over Perfection

In Vibe Mode, Optimize For:

  1. Working software over perfect code
  2. User value over technical elegance
  3. Fast feedback over comprehensive testing
  4. Learning over planning

Read the full file on GitHub · 226 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. yesterday First seen · 226 lines · 0 tokens per session scan A 085a294a99c3

Subscribe to this mod's changes

80-vibe-coding is a cursor rule published in the GitHub repository Luxvil/ai-coding-rules (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,301 tokens. A static security scan graded it A with 0 findings. It is 100% identical to 80-vibe-coding, differing in 0 lines, and is treated as a copy.