SpliceKit CLAUDE.md

Instructions for controlling Final Cut Pro, Apple's video-editing application, through direct program calls sent to a local JSON-RPC server. It forbids keyboard simulation, AppleScript, menu clicking, and accessibility-based UI control.

In plain words
What is it for?
Use it to inspect and edit Final Cut Pro timelines, sequences, clips, and markers through direct object calls or supported bridge commands.
Why use it?
It sets a single programmatic way to edit projects and avoids fragile interactions that depend on the visible application interface. It also requires checking project details before editing or opening one.

Instructions file

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.

agentmods
npx agentmods add instructions/elliotttate/splicekit/claude-md
Clone the repo
git clone --depth 1 https://github.com/elliotttate/SpliceKit
Per session 12,190 This file is loaded in full into every session.
When invoked 12,190 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.12190 $0.12190
Opus 5 $0.06095 $0.06095
Sonnet 5 $0.02438 $0.02438
Haiku 4.5 $0.01219 $0.01219

Measured 3d ago against content hash 2fdafe202309, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SpliceKit CLAUDE.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 3d 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

This is a copy

86% identical to SpliceKit AGENTS.md — 215 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 1,097 lines

How it starts

The opening of the file, as written. The whole thing — 1,097 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpliceKit - Programmatic Final Cut Pro Control

SpliceKit is an ObjC dylib injected into FCP's process. It exposes all 78,000+ ObjC classes via a JSON-RPC server on TCP 127.0.0.1:9876. Everything is fully programmatic -- no AppleScript, no UI automation, no menu clicks.

NEVER Use Keyboard Simulation or AppleScript

All FCP actions MUST go through direct ObjC calls. Never use any of these:

  • SpliceKit_simulateKeyPress() or synthetic NSEvent key events
  • CGEvent keyboard/mouse posting
  • osascript / NSAppleScript / AppleScript tell application
  • Accessibility APIs (AXUIElement) for clicking or typing
  • Frame-stepping loops (nextFrame x N) when seekToTime exists

Instead, always use one of these patterns (in priority order):

  1. Direct method call on the timeline/sequence/clip object via objc_msgSend
  2. Responder chain via [NSApp sendAction:NSSelectorFromString(@"selector:") to:nil from:nil]
  3. Batch bridge endpoint (e.g. timeline.addMarkers) for operations on multiple items
  4. Menu execute via menu.execute for actions only accessible through menus

If an action doesn't have a direct ObjC selector yet, find one using explore_class / search_methods on the relevant class (FFAnchoredTimelineModule, FFAnchoredSequence, etc.) rather than simulating the keyboard shortcut.

Quick Start

1. bridge_status()                    -- verify connection
2. open_project("My Project")         -- open a project by name
3. get_timeline_clips()               -- see timeline contents
4. timeline_action("blade")           -- edit
5. verify_action("after blade")       -- confirm state changed
6. capture_timeline()                 -- visually verify the timeline
7. capture_viewer()                   -- visually verify the viewer/canvas

CRITICAL: Must Know Before Editing

Opening a Project

Use open_project() to load a project by name:

open_project("My Project")                   # find by name
open_project("Edit v2", event="4-5-26")      # filter by event too

Read the full file on GitHub · 1,097 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. 3d ago First seen · 1,097 lines · 12,190 tokens per session scan A 2fdafe202309

Subscribe to this mod's changes

SpliceKit CLAUDE.md is an instructions file published in the GitHub repository elliotttate/SpliceKit (131 stars, last pushed 4d ago), licensed MIT. It adds 12,190 tokens to every session, about $0.0609 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to SpliceKit AGENTS.md, differing in 215 lines, and is treated as a copy.

Related

Other instructions, from other repositories

fcp-mcp-server CLAUDE.md

Claude Code instructions for DareDev256/fcp-mcp-server, covering claude.md — fcp-mcp-server, what this is, architecture, key patterns and running.

DareDev256/fcp-mcp-server · 2,131 tokens

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 · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens