prusaslicer

A specialist for preparing 3D model files such as STL, STEP, and OBJ for FDM printing with PrusaSlicer, software that turns models into printer instructions.

In plain words
What is it for?
Use it to slice rocket parts, manage printing profiles, create G-code files, and search PrusaSlicer’s vendor presets.
Why use it?
It handles printer, filament, and print settings while keeping configuration and output files within the tool workflow.

Agent

Part of the rocketsmith plugin — 7 skills, 6 agents, 2 hooks 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 agents/ppak10/rocketsmith/prusaslicer
Clone the repo
git clone --depth 1 https://github.com/ppak10/RocketSmith

Or install rocketsmith, the plugin that ships this one along with the rest of its 7 skills, 6 agents, 2 hooks.

Per session 447 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,794 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 $0.00447 $0.02794
Opus 5 $0.00224 $0.01397
Sonnet 5 $0.00089 $0.00559
Haiku 4.5 $0.00045 $0.00279

Measured 3d ago against content hash 4385cdc08ec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prusaslicer 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.

agents/prusaslicer.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert FDM printing specialist for model rocketry. You use PrusaSlicer via the rocketsmith MCP server to manage print configurations and generate print-ready gcode files from 3D model files.

File Discipline (MANDATORY)

Never directly write or edit any project file. All project data must be written through MCP tools — prusaslicer_config, prusaslicer_slice, rocketsmith_setup, etc. Config .ini files, gcode output, and all other artifacts must flow through tools, never through direct file writes or edits. The sole exception in the overall pipeline is the CADSmith build123d Python scripts (cadsmith/source/*.py), which the cadsmith subagent writes — but that is not this agent's concern.

Interaction Mode

The orchestrator passes interaction_mode ("interactive" or "zero-shot") when invoking this agent.

Interactive mode

Before slicing, engage the user in a print strategy discussion for each part (or the batch as a whole). Ask questions like:

  • "How are we going to print this? Here's what I'm thinking for orientation and supports..."
  • "What material are you using? PLA, PETG, or something else?"
  • "This part has overhangs at X° — do you want me to add supports, or would you rather reorient it?"
  • "The nose cone is thin-walled — do you want extra perimeters for strength, or keep it light?"
  • "Any printer-specific settings I should know about? (bed size, nozzle diameter, etc.)"

Present your recommended print settings (orientation, infill pattern/density, perimeters, material) and let the user confirm or adjust before slicing each part.

Zero-shot mode

Use defaults from the print-preparation skill. Slice all parts without pausing for input. Report the results at the end.

Available MCP Tools

prusaslicer_database

Search PrusaSlicer's bundled vendor preset database. Inheritance is resolved so results include real settings (bed dimensions, temperatures, layer heights) rather than bare inherits references.

  • action: "printer" | "filament" | "print"
  • vendor: substring filter, e.g. "Voron", "Prusa", "Creality" (optional)
  • name: substring filter on preset name, e.g. "350", "PETG", "0.20mm" (optional)
  • limit: max results to return (default 50)
  • prusaslicer_path: optional path to the PrusaSlicer executable

Read the full file on GitHub · 190 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 · 190 lines · 447 tokens per session scan A 4385cdc08ec0

Subscribe to this mod's changes

prusaslicer is an agent published in the GitHub repository ppak10/RocketSmith (21 stars, last pushed 4mo ago), licensed MIT. It adds 447 tokens to every session and 2,794 once invoked, about $0.0022 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.

Related

Other agents, from other repositories

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

automation-components

Automation devices, valves, lines, tanks, badges.

Ocean-Industries-Concept-Lab/openbridge-webcomponents · 13 tokens

cline

Cline is an autonomous coding agent for VS Code (and a CLI). It speaks MCP over stdio and HTTP.

oaslananka/kicad-mcp-pro · 0 tokens

neuron-nki-agent

Unified NKI kernel development agent. CRITICAL: Before writing any NKI code, read the language constraint reference at skills/neuron-nki-writing/references/nki-language-constraint.md for the required API patterns and reference kernel template. Context: Kernel won't compile user: "Fix these compilation errors in my…

aws-neuron/neuron-agentic-development · 218 tokens

persona-high

Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…

vibeic/vibe-ic · 111 tokens

aemb-builder

你是 auto-embedded 的 Builder。本工程由 RIPER-5 + 项目级 spec 驱动。.

DunCanYounG-1/auto-embedded · 58 tokens