gcode-generate

gcode-generate is a skill for Claude Code from brs077/CNC-design-control-MCP. It costs 47 tokens per session (406 once invoked), scanned A, original, MIT.

A skill for creating G-code, the text instructions that control CNC machines. It supports toolpaths for cutting profiles, clearing pockets, drilling holes, and leveling surfaces, with settings for tools, depths, feeds, and spindle speed.

In plain words
What is it for?
Use it to generate .nc files for shapes, rectangular or circular pockets, drilling patterns, and surface-facing operations.
Why use it?
It turns common machining operations into machine-readable paths and helps organize the cutting settings needed for each operation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cncjs-mcp plugin — 12 skills, 4 commands, 1 MCP server shipped together

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 skills/brs077/cnc-design-control-mcp/gcode-generate
Any agent
npx skills add brs077/CNC-design-control-MCP --skill gcode-generate
Clone the repo
git clone --depth 1 https://github.com/brs077/CNC-design-control-MCP

Made for: Claude Code.

Or install cncjs-mcp, the plugin that ships this one along with the rest of its 12 skills, 4 commands, 1 MCP server.

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 gcode-generate

README.md
[![agentmods](https://agentmods.dev/badge/skills/brs077/cnc-design-control-mcp/gcode-generate.svg)](https://agentmods.dev/skills/brs077/cnc-design-control-mcp/gcode-generate)
Your own site
<a href="https://agentmods.dev/skills/brs077/cnc-design-control-mcp/gcode-generate"><img src="https://agentmods.dev/badge/skills/brs077/cnc-design-control-mcp/gcode-generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00406
Opus 5 $0.00023 $0.00203
Sonnet 5 $0.00009 $0.00081
Haiku 4.5 $0.00005 $0.00041

Measured 5d ago against content hash eddf7d0ca802, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gcode-generate 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 5d 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.

skills/gcode-generate/SKILL.md · 39 lines

What it actually says

G-code Generation

Generate ready-to-run G-code toolpaths for common CNC operations.

Available MCP Tools

  • generate_gcode_profile — Cut 2D shapes (rectangle, circle, or custom points) with multi-pass step-down. Supports inside/outside/on-line cutting with tool radius compensation.
  • generate_gcode_pocket — Clear rectangular or circular pockets with zigzag or spiral strategies. Multi-pass depth with configurable stepover.
  • generate_gcode_drill — Drilling patterns (single, grid, circular, or custom coordinates) with optional peck drilling for chip clearing.
  • generate_gcode_facing — Surface facing/leveling operations with configurable stepover and climb/conventional milling direction.

Parameters Common to All

  • outputPath — Where to save the generated .nc file
  • spindleSpeed — RPM (default varies by operation)
  • feedRate — Cutting feed rate in mm/min
  • depthOfCut — Total depth to cut
  • stepDown — Depth per pass
  • toolDiameter — Cutter diameter in mm

Workflow

  1. Discuss the part geometry and material with the user
  2. Determine appropriate feeds, speeds, and depths for the material
  3. Generate the G-code with the appropriate tool
  4. Use analyze_gcode to verify bounding box and moves
  5. Use load_gcode to load into CNCjs for execution

Tips

  • Always verify the generated G-code bounds fit the workpiece
  • Use conservative feeds and speeds for first cuts
  • Step-down should typically be 1/2 to 1x tool diameter for wood, less for metal
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. 5d ago First seen · 39 lines · 47 tokens per session scan A eddf7d0ca802

Subscribe to this mod's changes

gcode-generate is a skill published in the GitHub repository brs077/CNC-design-control-MCP (1 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 406 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 2026-08-31.

Related

Other skills, from other repositories

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens