project-ai

project-ai is a cursor rule for Cursor from iamadi11/mcp-ui-poc. It costs 547 tokens per session, scanned A, original, MIT.

A set of project rules covering the required workflow, technology choices, security, testing, and code layout. It describes a monorepo, meaning one repository containing multiple related projects: a Node.js and Express server and a React frontend.

In plain words
What is it for?
It guides work on the server and client, including linting, builds, manual checks, architecture boundaries, and installation.
Why use it?
It gives an agent consistent instructions for exploring, changing, testing, and documenting this project.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit It guides work on the server and client, including linting, builds, manual…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/iamadi11/mcp-ui-poc/project-ai
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.

Clone the repo
git clone --depth 1 https://github.com/iamadi11/mcp-ui-poc

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 project-ai

README.md
[![agentmods](https://agentmods.dev/badge/rules/iamadi11/mcp-ui-poc/project-ai.svg)](https://agentmods.dev/rules/iamadi11/mcp-ui-poc/project-ai)
Your own site
<a href="https://agentmods.dev/rules/iamadi11/mcp-ui-poc/project-ai"><img src="https://agentmods.dev/badge/rules/iamadi11/mcp-ui-poc/project-ai.svg" alt="Measured on agentmods" height="20"></a>
Per session 547 This file is loaded in full into every session.
When invoked 547 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00547 $0.00547
Opus 5 $0.00273 $0.00273
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured 7d ago against content hash 87457f0b3f38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

project-ai 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 7d 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/project-ai.mdc · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor — project rules

Canonical workflow

Follow docs/AI_WORKFLOW.md for the mandatory sequence (research → plan → test definition → implement → tests → validate → document → instrument), testing expectations, architecture boundaries, security, and code exploration order. Do not contradict it; one-line exceptions with rationale only.

Stack & layout

  • Stack: Node.js (ES modules), Express in server/, React 18 + Vite in client/.
  • Client UI: Glass-style UI with tunable blur/mesh (client/src/glassAppearance.js); system light/dark via CSS variables in client/src/App.css (no component library).
  • Monorepo: Root package.json (server + scripts); client/package.json (frontend). Install: npm install at root; npm run install-all for both trees.

Mandatory checks

  • After changing client/ JS/JSX: run npm run lint from client/ when ESLint is configured there (see docs/AI_WORKFLOW.md). Otherwise use editor diagnostics and npm run build.
  • Validate changed flows manually (see README.md for dev servers and ports).

Architecture

  • Keep API and MCP server logic in server/; UI only in client/src/.
  • Avoid circular server/ imports; prefer clear module boundaries per docs/AI_WORKFLOW.md.

Security

  • Secrets only via environment variables / secret managers; use .env locally (gitignored). Never commit secrets or put them in prompts, logs, or agent output.

Exploration policy

Structured navigation first: README.md, docs/AI_WORKFLOW.md, CLAUDE.md, then scoped search in server/ or client/ before whole-repo grep. MCP (when enabled): cursor-ide-browser for UI verification; user-ai-agent-committee if configured — read tool schemas before calling.

Claude Code parity

Project instructions for Claude Code live in CLAUDE.md; skills live under .claude/skills/. Keep these aligned with docs/AI_WORKFLOW.md.

Read the full file on GitHub · 39 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. 7d ago First seen · 39 lines · 547 tokens per session scan A 87457f0b3f38

Subscribe to this mod's changes

project-ai is a cursor rule published in the GitHub repository iamadi11/mcp-ui-poc (8 stars, last pushed 2mo ago), licensed MIT. It adds 547 tokens to every session, about $0.0027 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.