nuke-mcp: Instructions file for Claude Code

CLAUDE.md

nuke-mcp CLAUDE.md is an instructions file for Claude Code from kleer001/nuke-mcp. It costs 574 tokens per session, scanned A, original, MIT.

Project instructions for an MCP connection to Nuke, a professional application for visual compositing. They describe the bridge between Nuke, the MCP server, and the AI client, including rules for risky changes.

In plain words
What is it for?
Use them when operating Nuke through MCP to inspect scripts and nodes, modify a composition, delete nodes, execute code, or load another script.
Why use it?
They prevent accidental deletion, script replacement, or code execution by requiring the current state to be inspected and destructive actions to be confirmed first.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kleer001/nuke-mcp's own configuration. It tells Claude Code how to work on nuke-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 nuke-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kleer001/nuke-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/kleer001/nuke-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kleer001/nuke-mcp

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.

agentmods badge for nuke-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kleer001/nuke-mcp/claude-md.svg)](https://agentmods.dev/instructions/kleer001/nuke-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kleer001/nuke-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kleer001/nuke-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 574 This file is loaded in full into every session.
When invoked 574 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 $0.00574 $0.00574
Opus 5 $0.00287 $0.00287
Sonnet 5 $0.00115 $0.00115
Haiku 4.5 $0.00057 $0.00057

Measured 8d ago against content hash 4549e3e44560, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

nuke-mcp 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 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.

CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NukeMCP — AI Behavior Rules

You are connected to a live Nuke compositing session via MCP. Follow these rules.

Architecture

Three-layer system:

  1. Nuke Addon — socket server running inside Nuke (port 54321)
  2. MCP Server (src/nukemcp/) — FastMCP bridge, exposes tools via stdio
  3. AI Client — you, reading this file

Destructive Actions

Never perform destructive actions without explicit user confirmation:

  • delete_node — always call first with confirm=False to show what would be deleted, then confirm with the user before calling with confirm=True
  • execute_python — always show the code to the user first, then confirm before calling with confirm=True
  • load_script — always warn that the current script will be replaced, then confirm

The pattern:

  1. Call the tool with confirm=False (returns a description of what would happen)
  2. Show the description to the user
  3. Ask for confirmation
  4. Only if confirmed, call again with confirm=True

Before Making Changes

  • Call get_script_info to understand the current state
  • Call get_node_info on relevant nodes before modifying them
  • Never assume what nodes exist — always check first
  • Read error messages carefully; they tell you what went wrong

Node Naming

Use descriptive, lowercase names with underscores:

  • fg_key not Keyer1
  • bg_grade not Grade3
  • hero_merge not Merge1
  • plate_read not Read1

Node Organization

  • Keep the graph flowing top-to-bottom
  • Source nodes (Read) at the top, output nodes (Write) at the bottom
  • Use auto_layout after creating multi-node setups
  • Position related nodes near each other

Colorspace

  • Respect the project's working colorspace — check with get_script_info
  • Never change colorspace settings without asking
  • When creating Read nodes, mention the expected colorspace if relevant

Memory

  • On session start, read nuke://memory/facility and nuke://memory/corrections resources for context
  • After any correction by the compositor, call log_correction to persist it for future sessions
  • Periodically call update_project_memory to keep the project snapshot current
  • If facility conventions exist, follow them (colorspace, naming, preferred tools)

Read the full file on GitHub · 66 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. 8d ago First seen · 66 lines · 574 tokens per session scan A 4549e3e44560

Subscribe to this mod's changes

nuke-mcp CLAUDE.md is an instructions file published in the GitHub repository kleer001/nuke-mcp (9 stars, last pushed 5mo ago), licensed MIT. It adds 574 tokens to every session, about $0.0029 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.

Related

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.

vercel/next.js · 7,296 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 · 5,153 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

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

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 · 4,469 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