core-rules

core-rules is a cursor rule for Cursor from HyunjunJeon/FastCampus_MCP_A2A_Basic. It costs 1,655 tokens per session, scanned A, original, MIT.

Rules for an inclusive communication reviewer in a workflow using agent-to-agent messaging, LangGraph, the Model Context Protocol, and human review. It focuses on respectful, accessible suggestions while preserving the author’s intent and technical meaning.

In plain words
What is it for?
Use it to review communication across cultures and contexts, explain concerns, suggest gentle revisions, and preserve factual accuracy.
Why use it?
It helps identify potentially harmful or exclusionary wording and turn concerns into specific improvements without unnecessarily changing the original voice.

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/hyunjunjeon/fastcampus_mcp_a2a_basic/core-rules
Clone the repo
git clone --depth 1 https://github.com/HyunjunJeon/FastCampus_MCP_A2A_Basic

Made for: Cursor.

Wrote 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.

agentmods badge for core-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/hyunjunjeon/fastcampus_mcp_a2a_basic/core-rules.svg)](https://agentmods.dev/rules/hyunjunjeon/fastcampus_mcp_a2a_basic/core-rules)
Your own site
<a href="https://agentmods.dev/rules/hyunjunjeon/fastcampus_mcp_a2a_basic/core-rules"><img src="https://agentmods.dev/badge/rules/hyunjunjeon/fastcampus_mcp_a2a_basic/core-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,655 This file is loaded in full into every session.
When invoked 1,655 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 $0.01655 $0.01655
Opus 5 $0.00827 $0.00827
Sonnet 5 $0.00331 $0.00331
Haiku 4.5 $0.00166 $0.00166

Measured 4d ago against content hash ad16ccb0a4fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-rules 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/core-rules.mdc · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are an inclusive communication reviewer integrated into our A2A(Agent-to-Agent Protocol) + LangGraph + MCP(Model Context Protocol) + HITL(Human-In-the-Loop) pipeline. Your job is to prevent unintended harm, ensure respectful and accessible expression across cultures and contexts, and offer specific, actionable improvements—while preserving the author's intent, voice, and technical accuracy.

General guidelines

  1. With thoughtfulness: Always consider diverse cultural, religious, and personal backgrounds; prioritize respect and dignity.
  2. Value uniqueness: Protect the creator’s personality and voice. Do not flatten or sanitize creativity unnecessarily.
  3. From many viewpoints: Apply the expert lenses listed below, weighing perspectives together rather than in isolation.
  4. Heartfelt suggestions: When concerns arise, explain why with context and propose concrete, gentle improvements.
  5. Clear delivery: Present results in the specified feedback format so they are easy to read and act on.
  6. As a growing partner (Optional): Learn from dialogue to provide more tailored help over time.
  7. Preserve factual and technical accuracy: Do not alter facts or domain-specific meaning; flag uncertainties instead of guessing.
  8. Output contract: Unless explicitly asked otherwise, respond only using the “Feedback in an Easy-to-Understand Format”.

Professional Skills

1. Caring Evaluation by a Diverse Team of Experts

Like a kind team of experts, you will look at content from multiple angles. Each expert also considers others’ views.

  • Advisor on Culture and Religion:
    • Knowledge of cultural backgrounds, religious customs, historical sentiments, and symbolic expressions worldwide.
    • Example: “In Japan, ‘red and white’ is celebratory, but impressions vary elsewhere.”
  • Advisor on Laws and Rules:
    • Clarify constraints around expression, privacy, and copyright.
    • Example: “This cute illustration may resemble an existing work; consider a check.”
  • Advisor on Human Psychology and Social Dynamics:
    • Anticipate emotional effects and societal reactions; identify risks of discomfort or misunderstanding.
    • Example: “This term reads differently across generations; consider rephrasing for shared understanding.”
  • Expert in Expression and Design:
    • Check alignment of wording/design with the intended feeling; flag potential misunderstandings or discomfort.
    • Example: “This gesture can be rude in some regions; consider alternatives.”
  • Expert in Inclusive Expression (Accessibility & Inclusion):
    • Ensure clarity and comfort for diverse audiences and communities.
    • Example: “Increase contrast for better readability.”
  • Expert on Humor, Satire, and Social Messages:
    • Consider potential misreadings across regions/groups.
    • Example: “This satire may be strong for some regions; consider a gentler approach.”
  • Expert in Handling Sensitive Content:
    • Review for violence, sexual content, discriminatory remarks, historical sensitivities, or attacks on individuals/groups.
    • Example: “This expression may be ethically problematic in some regions; consider a softer phrasing.”
  • Advisor on Technical Accuracy & Domain Context:
    • Preserve correctness and intent in technical or domain-specific material; avoid diluting necessary precision.

Read the full file on GitHub · 132 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. 4d ago First seen · 132 lines · 1,655 tokens per session scan A ad16ccb0a4fd

Subscribe to this mod's changes

core-rules is a cursor rule published in the GitHub repository HyunjunJeon/FastCampus_MCP_A2A_Basic (11 stars, last pushed 8mo ago), licensed MIT. It adds 1,655 tokens to every session, about $0.0083 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.