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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00534 | $0.00534 |
| Opus 5.5 | $0.00214 | $0.00214 |
| Sonnet 5.5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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 1mo 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.
What it actually says
Cursor — project rules
Canonical workflow
Follow docs/AI_WORKFLOW.md. Non-trivial work starts with /ask-matt. Do not contradict the workflow; one-line exceptions with rationale only. Glossary: CONTEXT.md.
Stack & layout
- Stack: Node.js (ES modules), Express in
server/, React 18 + Vite inclient/. - Client UI: Chat studio in
client/src/studio/. Readdesign-system/MCP-UI/MASTER.mdbefore JSX. Host chrome is shadcn; generated HTML uses ThemeAdapter inpackages/core/src/design-systems/. - Monorepo: Root
package.json;client/package.json.npm installat root;npm run install-all;npm run skills:installafter clone.
Mandatory checks
- After changing
client/JS/JSX: runnpm run lintfromclient/. - After
packages/core: runnpm test. - Validate changed flows (see
README.md).
Architecture
- Keep API and MCP server logic in
server/; UI only inclient/src/. - Jev fan-out decides;
applyPolicyhydrates; Claude only on low confidence /needs_llm. Never send full payloads to an LLM. - Avoid circular
server/imports.
Security
- Secrets only via environment variables. Local:
.env.local. Never commit secrets or put them in prompts, logs, or agent output.
Exploration policy
Structured navigation first: README.md, CONTEXT.md, docs/AI_WORKFLOW.md, CLAUDE.md, then scoped search in server/ or client/. MCP: cursor-ide-browser; user-ai-agent-committee if configured — read tool schemas before calling.
Claude Code parity
Project instructions live in CLAUDE.md; skills under .claude/skills/. Matt tdd/code-review replace duplicate playbooks.
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.
- 1mo ago Changed · +2 lines · -13 tokens per session a92ce7fdd748
- 2mo 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 1mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0021 per session on Opus 5.5. 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.
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.
family-instance-domain-actions
Family instance domain action implementation patterns.