premiere-pro-mcp: Instructions file for Codex

AGENTS.md

premiere-pro-mcp AGENTS.md is an instructions file for Codex, OpenCode from leancoderkavy/premiere-pro-mcp. It costs 3,300 tokens per session, scanned A, original, MIT.

A repository instruction file for coding agents working with a TypeScript server that controls Adobe Premiere Pro through an MCP connection. MCP is a standard way for an AI client to call tools provided by another program.

In plain words
What is it for?
Use it as the starting guidance for changing or reviewing this Premiere Pro integration repository. It explains the local Node.js server, the Premiere panel, and their file-based communication.
Why use it?
It gives coding agents the repository's architecture, naming, and source-of-truth rules so they do not confuse generated files with canonical instructions or misunderstand how the Premiere connection works.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is leancoderkavy/premiere-pro-mcp's own configuration. It tells Codex and OpenCode how to work on premiere-pro-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything premiere-pro-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to leancoderkavy/premiere-pro-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/leancoderkavy/premiere-pro-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/leancoderkavy/premiere-pro-mcp

Made for: Codex, OpenCode.

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 premiere-pro-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/leancoderkavy/premiere-pro-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leancoderkavy/premiere-pro-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,300 This file is loaded in full into every session.
When invoked 3,300 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 $0.03300 $0.03300
Opus 5.5 $0.01320 $0.01320
Sonnet 5.5 $0.00660 $0.00660
Haiku 4.5 $0.00330 $0.00330

Measured 22d ago against content hash 50cae7c5014e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

premiere-pro-mcp AGENTS.md 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 22d 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.

AGENTS.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical instructions for any IDE or coding agent working in this repository. Cursor, GitHub Copilot, Codex, Claude Code, Gemini CLI, Windsurf, and similar tools should start here.

This is not the product website LLM crawl file. That file is https://premiere-pro-mcp.com/llms.txt, generated in the separate website repository.

Adapter stubs (CLAUDE.md, GEMINI.md, CONVENTIONS.md, .github/copilot-instructions.md, .cursor/rules/, .windsurf/rules/, .clinerules, .continue/rules/, .junie/guidelines.md) point here. Keep those stubs thin; put durable guidance in this file or in a focused Cursor/Copilot path rule. Optional Cursor rule .cursor/rules/jev-surfaces.mdc scores CEP / UXP / claims file candidates. It is not a TypeSafe Jev sidecar protocol; do not add one here.

What this repository is

Independent TypeScript MCP server that gives a compatible AI client structured control over supported Adobe Premiere Pro workflows. Display name: MCP for Adobe Premiere Pro. npm package: premiere-pro-mcp. MCP server name: io.github.leancoderkavy/premiere-pro.

It is not affiliated with Adobe. The only npm package published from this repo is premiere-pro-mcp.

Production path: local Node.js MCP server (stdio) talking to a CEP panel inside Premiere through private file-based IPC (.jsx command files and .json responses). UXP is a capability-aware preview backend for Premiere 25.6+ documented APIs. A failed UXP mutation must never be silently retried through CEP or the undocumented QE DOM.

The local stdio server is the product. The HTTP /mcp endpoint is an operator-managed transport, not a public remote-Premiere product. See docs/hosted-mcp-product-boundary.md.

Canonical sources

Read only what the task needs. Current source and release metadata beat dated snapshots.

Topic Source
Product, setup, architecture overview README.md
This agent map AGENTS.md (this file)
Trust model and vulnerability reports SECURITY.md
Human contributor workflow CONTRIBUTING.md
API research (dated; not live counts) RESEARCH.md
Registered tool catalog docs/supported-actions.md (generated)
Product claims governance docs/claims-registry.md, docs/claims-registry.json
Published-package facts npm tarball, synced by leancoderkavy/premiere-pro-mcp-site to https://premiere-pro-mcp.com/facts/
Development source metadata release-metadata.json
Release titles, tags, and versions docs/release-conventions.md
MCP runtime instructions for clients src/workflows/agent-instructions.ts
Hosted HTTP boundary docs/hosted-mcp-product-boundary.md
UXP 26.3 coverage docs/adobe-uxp-26.3-coverage.md
Claude Code develop skill claude-plugins/premiere-pro/skills/develop-premiere-pro-mcp/SKILL.md

Read the full file on GitHub · 214 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. 22d ago Changed · +12 lines · +177 tokens per session 50cae7c5014e
  2. 27d ago Changed · -8 lines · -56 tokens per session dc12a26a795f
  3. 1mo ago Changed · +24 lines · +395 tokens per session 6abf176659f7
  4. 1mo ago Changed · +44 tokens per session 86448b4665ed
  5. 1mo ago First seen · 186 lines · 2,740 tokens per session scan A 76e6aec3ca7f

Subscribe to this mod's changes

premiere-pro-mcp AGENTS.md is an instructions file published in the GitHub repository leancoderkavy/premiere-pro-mcp (440 stars, last pushed yesterday), licensed MIT. It adds 3,300 tokens to every session, about $0.0132 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 2026-09-20.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens