vibe-coding-core

Core rules for a Cursor coding agent working under a canonical AGENTS.md file. They cover thinking before coding, simple and focused edits, verification, and attention to product and interface quality.

In plain words
What is it for?
Use them when editing code in Cursor, especially for multi-file changes, architecture work, debugging, handoffs, and user-interface updates.
Why use it?
They give the agent consistent boundaries for making changes and reduce speculative refactoring, missed interface states, and unverified 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/sarutobisasuke8/agentops-template/vibe-coding-core
Clone the repo
git clone --depth 1 https://github.com/SarutobiSasuke8/agentops-template

Made for: Cursor.

Per session 280 This file is loaded in full into every session.
When invoked 280 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 $0.00280 $0.00280
Opus 5 $0.00140 $0.00140
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash 0c18a1efdab5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-coding-core 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 2d 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/vibe-coding-core.mdc · 28 lines

What it actually says

Vibe Coding Core Rule

Canonical source: AGENTS.md

Follow AGENTS.md. This rule holds Cursor-specific guidance only; the canonical principles live in AGENTS.md.

Alignment Markers

  • Think Before Coding — inspect context, surface assumptions, ask when ambiguity changes implementation.
  • Simplicity First — prefer the smallest verifiable solution; avoid speculative abstractions and dependencies.
  • Surgical Changes — keep edits scoped, preserve existing style, avoid drive-by refactors.
  • Goal-Driven Execution — define success criteria and verify changed behavior.
  • Vibe Coding Quality Bar — protect the product feeling, responsive UI, core workflows, and polish.

Cursor Behavior

  • Inline edits should stay small (target under ~50 lines per accepted edit) unless the user asked for a larger rewrite.
  • Ground edits in the current file and nearby project conventions.
  • Preserve user-authored comments and docs.
  • For UI changes, account for loading, empty, error, hover/focus, and responsive states where relevant.
  • Mention unrelated issues separately instead of silently editing them.
  • For multi-file, architecture, debugging, or handoff-heavy work, append a session log in Session Logs/ using Templates/SESSION_LOG_TEMPLATE.md.
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. 2d ago First seen · 28 lines · 280 tokens per session scan A 0c18a1efdab5

Subscribe to this mod's changes

vibe-coding-core is a cursor rule published in the GitHub repository SarutobiSasuke8/agentops-template (9 stars, last pushed 13d ago), licensed MIT. It adds 280 tokens to every session, about $0.0014 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.