resolve-audio

resolve-audio is a cursor rule for Cursor from samuelgursky/davinci-resolve-mcp. It costs 47 tokens per session (356 once invoked), scanned A, original, MIT.

A set of rules for handling audio and Fairlight tasks in DaVinci Resolve, including audio settings, syncing, voice isolation, subtitles, loudness, routing, and file operations.

In plain words
What is it for?
Use it to plan tracks and buses, inspect loudness and audio coverage, apply safe audio properties, sync recordings, generate subtitles, isolate voice, or split and convert audio files.
Why use it?
It separates offline planning from live Resolve changes and protects source media by requiring derived files to be written separately.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit Use it to plan tracks and buses, inspect loudness and audio coverage, apply safe audio properties, sync recordings, generate subtitles, isolate voice, or split and convert audio files.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/samuelgursky/davinci-resolve-mcp/resolve-audio
About the project

davinci-resolve-mcp is an MCP server that lets AI assistants control DaVinci Resolve Studio through its scripting API, including editing, media organization, rendering, grading, and other project tasks. It is for users who want agents to operate Resolve and inspect media through a local control panel. The catalogue entries support agent workflows for this Resolve integration.

samuelgursky/davinci-resolve-mcp · 2,508 stars · on GitHub

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/samuelgursky/davinci-resolve-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 resolve-audio

README.md
[![agentmods](https://agentmods.dev/badge/rules/samuelgursky/davinci-resolve-mcp/resolve-audio.svg)](https://agentmods.dev/rules/samuelgursky/davinci-resolve-mcp/resolve-audio)
Your own site
<a href="https://agentmods.dev/rules/samuelgursky/davinci-resolve-mcp/resolve-audio"><img src="https://agentmods.dev/badge/rules/samuelgursky/davinci-resolve-mcp/resolve-audio.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 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 $0.00047 $0.00356
Opus 5 $0.00023 $0.00178
Sonnet 5 $0.00009 $0.00071
Haiku 4.5 $0.00005 $0.00036

Measured 6d ago against content hash b17f5a5ca1ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

resolve-audio 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/resolve-audio.mdc · 16 lines

What it actually says

Resolve Audio / Fairlight work. Apply when: setting audio properties, syncing audio, isolating voice, generating subtitles, planning Fairlight tracks/buses, checking loudness, routing buses, or splitting/trimming/converting audio.

Two servers — compute offline, apply live:

  • Live (running Resolve, davinci-resolve): timeline (probe_audio_item|track, safe_set_audio_properties, safe_auto_sync_audio, voice_isolation_capabilities, subtitle_generation_probe, fairlight_boundary_report)
  • Offline (.drp/.drt/.drx + DB, no Resolve, davinci-resolve-advanced): audio_plan (track_plan, analyze_coverage, check_loudness), fairlight (bus routing — patches FLStudioModelBA, no scripting API), audio (split/trim/convert)
  • Key rule: Plan/measure offline, apply live. Bus routing has no scripting API — use fairlight (needs better-sqlite3; project CLOSED + quit/relaunch). audio ops need ffmpeg on PATH and write NEW files to scratch, never over source.

Depth: docs/kernels/audio-fairlight-kernel.md. On-demand in any MCP client: the /audio_workflow slash prompt. Portable skill: resolve-audio in .agents/skills/. Never modify/transcode/derive source media (AGENTS.md).

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. 6d ago Changed b17f5a5ca1ab
  2. 9d ago First seen · 16 lines · 47 tokens per session scan A 2a1b4b6f5b00

Subscribe to this mod's changes

resolve-audio is a cursor rule published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,508 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 356 once invoked, about $0.0002 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 2026-08-30.