uxp

uxp is a cursor rule for Cursor from leancoderkavy/premiere-pro-mcp. It costs 0 tokens per session (278 once invoked), scanned A, original, MIT.

A set of coding rules for connecting a Premiere Pro panel to Adobe's newer UXP extension system. It covers capability checks, safe file paths, undoable changes, and keeping the panel code consistent.

In plain words
What is it for?
It is for developing and maintaining UXP-based Premiere Pro tools, including panel commands, lint checks, native readback, and MCP tool mappings.
Why use it?
It helps prevent the panel from calling unavailable Premiere features, reporting unconfirmed changes as successful, or escaping the approved workspace.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It is for developing and maintaining UXP-based Premiere Pro tools, including panel commands, lint checks, native readback, and MCP tool mappings.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/leancoderkavy/premiere-pro-mcp/uxp
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/leancoderkavy/premiere-pro-mcp

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 uxp

README.md
[![agentmods](https://agentmods.dev/badge/rules/leancoderkavy/premiere-pro-mcp/uxp/github.svg)](https://agentmods.dev/rules/leancoderkavy/premiere-pro-mcp/uxp)
Your own site
<a href="https://agentmods.dev/rules/leancoderkavy/premiere-pro-mcp/uxp"><img src="https://agentmods.dev/badge/rules/leancoderkavy/premiere-pro-mcp/uxp/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.

agentmods 80×15 button for uxp

Your own site · 80×15
<a href="https://agentmods.dev/rules/leancoderkavy/premiere-pro-mcp/uxp"><img src="https://agentmods.dev/badge/rules/leancoderkavy/premiere-pro-mcp/uxp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 278 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00278
Opus 5.5 $0.00000 $0.00111
Sonnet 5.5 $0.00000 $0.00056
Haiku 4.5 $0.00000 $0.00028

Measured 26d ago against content hash 3427abbd2907, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uxp 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 26d 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/uxp.mdc · 23 lines

What it actually says

UXP

uxp-plugin/ is a capability-aware Premiere 25.6+ backend. CEP remains the production compatibility path.

  • Honor the runtime capability probe. Do not call APIs the connected host did not advertise.
  • Keep panel code in CommonJS (.cjs). npm run lint applies @adobe/eslint-plugin-premierepro to uxp-plugin/**/*.cjs.
  • Mutations need undoable transactions where Adobe documents them, plus native readback. Failed post-commit readback is committed_unverified, not success.
  • Never fall back from a failed UXP mutation to CEP or the QE DOM.
  • Path-based commands stay inside the operator-approved workspace folder. Do not send the folder token or native root path to the MCP server.
  • Map new panel commands to MCP tools in src/tools/uxp*.ts and update the matching docs/coverage matrix.
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. 26d ago First seen · 23 lines · 0 tokens per session scan A 3427abbd2907

Subscribe to this mod's changes

uxp is a cursor rule published in the GitHub repository leancoderkavy/premiere-pro-mcp (387 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 tokens. 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 2026-09-20.