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.
git clone --depth 1 https://github.com/iamadi11/mcp-ui-pocWrote 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.
[](https://agentmods.dev/rules/iamadi11/mcp-ui-poc/project-ai)<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>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.
| Model | Per session | Once 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 |
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.
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 inclient/. - Client UI: Glass-style UI with tunable blur/mesh (
client/src/glassAppearance.js); system light/dark via CSS variables inclient/src/App.css(no component library). - Monorepo: Root
package.json(server + scripts);client/package.json(frontend). Install:npm installat root;npm run install-allfor both trees.
Mandatory checks
- After changing
client/JS/JSX: runnpm run lintfromclient/when ESLint is configured there (seedocs/AI_WORKFLOW.md). Otherwise use editor diagnostics andnpm run build. - Validate changed flows manually (see
README.mdfor dev servers and ports).
Architecture
- Keep API and MCP server logic in
server/; UI only inclient/src/. - Avoid circular
server/imports; prefer clear module boundaries perdocs/AI_WORKFLOW.md.
Security
- Secrets only via environment variables / secret managers; use
.envlocally (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.
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.
- 7d ago First seen · 39 lines · 547 tokens per session scan A 87457f0b3f38
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.