Borrowing it
Nothing to install: this file belongs to andrisgauracs/Premiere-Claude-Plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrisgauracs/Premiere-Claude-Plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/andrisgauracs/Premiere-Claude-PluginWrote 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/instructions/andrisgauracs/premiere-claude-plugin/agents-md)<a href="https://agentmods.dev/instructions/andrisgauracs/premiere-claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/andrisgauracs/premiere-claude-plugin/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.
<a href="https://agentmods.dev/instructions/andrisgauracs/premiere-claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/andrisgauracs/premiere-claude-plugin/agents-md.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 | $0.02468 | $0.02468 |
| Opus 5 | $0.01234 | $0.01234 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
Premiere-Claude-Plugin 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 8d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Premiere Pro through the tool bridge
Instructions for an agent driving Adobe Premiere Pro via the premiere MCP
tools. OpenCode reads this file automatically from the project root; other
clients may need it pasted into a system prompt or rules file.
Tools are referred to below by their bare names (get_project_info). Your
client may namespace them by server — OpenCode exposes them as
premiere_get_project_info. Same tools either way.
What you are working with
A live Premiere Pro project on the user's machine. The tools call Premiere's real scripting API — every change appears immediately in their timeline. There is no sandbox and no preview. Treat it like editing someone's working document while they watch.
You cannot see or hear anything. No video frames, no waveforms, no rendered
output. You reason entirely over structured data: track listings, clip times,
and whatever the analysis pipeline recorded in footage_manifest.json. Never
claim something "looks good" or "flows well" — you have no basis for it. Report
structure, not aesthetics.
Start by orienting
Never edit a project you haven't read. In order:
get_bridge_capabilities— what's enabled, and what is deliberately absent. Saves you from proposing things that cannot work.get_project_info— confirm which project and sequence is open. If it isn't the one the user meant, stop and ask.get_active_sequence— track layout and clip counts.list_clips_on_trackper track — the actual contents.
Then say what you found before doing anything else.
Call tools directly. Never through the shell.
These are MCP tools. Invoke them the way you invoke any tool. Do not try to
run them as shell commands, import them in Python, or write [Function ...]
into a message — none of that works, and quoting problems with paths are a sign
you have gone down this road.
If you find yourself shell-escaping a media path, stop. Either pass
source_clip_id instead, or pass the path as a plain JSON string argument in a
direct tool call — quoting is not your problem to solve.
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.
- 8d ago First seen · 212 lines · 2,468 tokens per session scan A b8fd0da7f697
Premiere-Claude-Plugin AGENTS.md is an instructions file published in the GitHub repository andrisgauracs/Premiere-Claude-Plugin (8 stars, last pushed 23d ago), licensed MIT. It adds 2,468 tokens to every session, about $0.0123 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 instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.