What is capcut-ai-editor CLAUDE.md?

Project instructions for an MCP server that helps Claude Code edit talking-head videos in CapCut, a video editing application.

Use them when developing or maintaining the SmartCut server and its CapCut project tools, with optional Whisper speech transcription and GPT-based duplicate detection.

They explain the project structure, settings, and workflow for reading subtitles, finding long silences, and identifying duplicate takes.

How mrbuslov/capcut-ai-editor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrbuslov/capcut-ai-editor. 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/mrbuslov/capcut-ai-editor/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mrbuslov/capcut-ai-editor

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mrbuslov/capcut-ai-editor/claude-md/github.svg)](https://agentmods.dev/instructions/mrbuslov/capcut-ai-editor/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mrbuslov/capcut-ai-editor/claude-md"><img src="https://agentmods.dev/badge/instructions/mrbuslov/capcut-ai-editor/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mrbuslov/capcut-ai-editor/claude-md"><img src="https://agentmods.dev/badge/instructions/mrbuslov/capcut-ai-editor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,051 This file is loaded in full into every session.

When invoked 1,051 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.

Model	Per session	Once invoked
Fable 5.1	$0.01051	$0.01051
Opus 5.5	$0.00420	$0.00420
Sonnet 5.5	$0.00210	$0.00210
Haiku 4.5	$0.00105	$0.00105

Measured 2mo ago against content hash 3b545fd82192, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

capcut-ai-editor 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 2mo 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.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SmartCut MCP Server — Project Context

What is this?

MCP server for automated "talking head" video editing. Works with Claude Code to:

Read CapCut's auto-generated subtitles
Heuristically find silences (gaps > 1 sec between subtitles)
Detect duplicate takes (keeps the last one)
Cut directly in the CapCut project (no backups, no copies)
Optionally use OpenAI GPT for better duplicate detection

Project Structure

src/smartcut/
├── __init__.py              # Version
├── config.py                # Settings, env vars, constants
├── server.py                # MCP server entry point, 8 tools
├── core/
│   ├── models.py            # Pydantic models (CapCutSubtitleSegment, etc.)
│   ├── whisper_client.py    # OpenAI Whisper API wrapper (optional)
│   ├── llm_client.py        # GPT for duplicate detection (optional)
│   ├── ffmpeg_utils.py      # FFmpeg audio extraction (optional, for Whisper)
│   ├── capcut_reader.py     # CapCut project reader/modifier + subtitle parser
│   └── capcut_finder.py     # CapCut project discovery
└── tools/
    └── capcut_projects.py   # All 8 MCP tools + heuristic analysis engine

Key Files

config.py

Settings class with env vars: OPENAI_API_KEY (optional), CAPCUT_DRAFTS_DIR
Constants: SILENCE_THRESHOLD_SEC = 1.0, DUPLICATE_SIMILARITY_THRESHOLD = 0.6

server.py

8 MCP tools:
- list_capcut_projects, open_capcut_project, smart_cut_project (original)
- edit_subtitle, split_subtitle, merge_subtitles, fix_word_timing, batch_edit_subtitles (subtitle corrections)

capcut_reader.py

CapCutProject class for loading/modifying existing CapCut projects
Key methods: load(), save(), get_subtitle_segments(), remove_time_ranges()
Subtitle corrections: edit_subtitle_text(), edit_subtitle_timing(), split_subtitle(), merge_subtitles(), fix_word_timing()
Reads draft_info.json (content) and draft_meta_info.json (metadata)

tools/capcut_projects.py

Main tool: smart_cut_project() — the core function
Heuristic engine: find_gaps(), find_duplicate_takes(), compute_text_similarity()
Subtitle correction wrappers: edit_subtitle(), split_subtitle(), merge_subtitles(), fix_word_timing(), batch_edit_subtitles()
Optional: _detect_duplicates_with_llm() for OpenAI-enhanced detection

Read the full file on GitHub · 96 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.

2mo ago First seen · 96 lines · 1,051 tokens per session scan A 3b545fd82192

Subscribe to this mod's changes

capcut-ai-editor CLAUDE.md is an instructions file published in the GitHub repository mrbuslov/capcut-ai-editor (123 stars, last pushed 12d ago), licensed MIT. It adds 1,051 tokens to every session, about $0.0042 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 2026-08-30.

Creative and media ai capcut mcp video

capcut-ai-editor CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
capcut-ai-editor CLAUDE.mdmrbuslov/capcut-ai-editor	Instructions file	123	12d ago	MIT	A	1,051	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

capcut-ai-editor: Instructions file for Claude Code