core

A set of repository rules that tells coding agents how to work in this project. It points them to the project's decisions, long-term notes, quality checks, and required engineering contract.

In plain words
What is it for?
Use it to guide planning, implementation, documentation updates, and completion checks in a code repository.
Why use it?
It keeps agent-made changes consistent with existing project decisions and prevents work from being declared complete without the required checks.

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/kingemma7/cursor-os/core
Clone the repo
git clone --depth 1 https://github.com/KingEmma7/cursor-os

Made for: Cursor.

Per session 232 This file is loaded in full into every session.
When invoked 232 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 $0.00232 $0.00232
Opus 5 $0.00116 $0.00116
Sonnet 5 $0.00046 $0.00046
Haiku 4.5 $0.00023 $0.00023

Measured yesterday against content hash eb8f537af1e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

template/.cursor/rules/core.mdc · 13 lines

What it actually says

The engineering contract for this repo lives in AGENTS.md (auto-loaded). Follow it. This rule only adds Cursor-specific behavior so the contract is not duplicated token-for-token on every request.

  • Consult project memory before non-trivial work: docs/repo-memory.md (durable facts), docs/decision-log.md (past decisions). Don't contradict a logged decision without flagging it.
  • When project-specific docs conflict, prefer the newest explicit decision in docs/decision-log.md, then update stale docs.
  • For multi-file, risky, or ambiguous changes, use Plan mode (or write a short plan) and get alignment before editing.
  • Gate completion on docs/quality-rubric.md. Don't claim done until its checks pass with evidence.
  • Keep memory current: when you learn a durable fact or make a notable decision, update docs/repo-memory.md or append to docs/decision-log.md.
  • If a rule, doc, or AGENTS.md claim is stale or wrong, fix it as part of your change instead of working around it.
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 · 13 lines · 232 tokens per session scan A eb8f537af1e9

Subscribe to this mod's changes

core is a cursor rule published in the GitHub repository KingEmma7/cursor-os (2 stars, last pushed 20d ago), licensed MIT. It adds 232 tokens to every session, about $0.0012 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.