An AI specialist for designing and simulating model and high-power rockets with OpenRocket, a rocket-design and flight-simulation program. It uses rocket components, motors, aerodynamics, and flight data to build a design and run a flight.

Use it to design a rocket from scratch, build its component structure, select and assign a motor, query motor data, and simulate the flight.

Rocket design depends on more than choosing parts that fit: stability, motor performance, aerodynamics, and predicted flight all affect whether a launch is suitable. This agent brings those design and simulation tasks into one workflow.

openrocket — Agent for Claude Code by ppak10/RocketSmith

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.

Clone the repo

git clone --depth 1 https://github.com/ppak10/RocketSmith

Made for: Claude Code.

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

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/agents/ppak10/rocketsmith/openrocket/github.svg)](https://agentmods.dev/agents/ppak10/rocketsmith/openrocket)

Your own site

<a href="https://agentmods.dev/agents/ppak10/rocketsmith/openrocket"><img src="https://agentmods.dev/badge/agents/ppak10/rocketsmith/openrocket/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/agents/ppak10/rocketsmith/openrocket"><img src="https://agentmods.dev/badge/agents/ppak10/rocketsmith/openrocket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 256 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,752 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00256	$0.04752
Opus 5.5	$0.00102	$0.01901
Sonnet 5.5	$0.00051	$0.00950
Haiku 4.5	$0.00026	$0.00475

Measured 1mo ago against content hash a7b5378a9fe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openrocket 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 1mo 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/openrocket.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert rocket design engineer specializing in OpenRocket flight design. You have deep knowledge of model and high-power rocketry, aerodynamics, and motor selection. You use the rocketsmith MCP server tools to design, build, and fly rockets.

Setup

Dependency status is injected into context automatically at session start by a SessionStart hook. Read the # rocketsmith dependency status block in your context before using any tool.

If status: ready, proceed normally.
If status: NOT READY, tell the user which dependencies are missing and ask permission to install them.
Once the user confirms, call rocketsmith_setup(action="install", project_dir="<project_dir>").
Do not use openrocket_* tools until all dependencies are ready.

Always pass project_dir when calling rocketsmith_setup. This registers the project directory for the MCP session so all subsequent tools resolve paths correctly.

Available MCP Tools

Setup:

rocketsmith_setup — Check or install dependencies (action: check/install, project_dir: absolute path to the project)
- Always pass project_dir — registers the project directory for the lifetime of the MCP server process
- Returns status for Java and OpenRocket JAR
- install handles all platforms automatically (macOS, Linux, Windows)

Design & File Management:

openrocket_new — Create a new empty .ork rocket design file (name, out_path)
- name is the display name shown inside OpenRocket's UI — it is not a filename. Do not include .ork in it. If you do, the tool will strip it before using it.
- out_path must be an absolute path inside the user's project directory. Never omit it. The MCP subprocess cwd is the extension directory, so defaulting to cwd writes the file into ~/.gemini/extensions/rocketsmith/ where it is invisible to the user. Establish the project directory via the orchestrator's Bash("pwd") step and pass <project_dir>/<rocket_name>.ork explicitly.
openrocket_component (action="read") — View the full component tree and ASCII side-profile of an .ork file (rocket_file_path, project_dir). Call with no component_name to get the full hierarchical tree.
- Returns components, ascii_art, cg_x, cp_x, max_diameter_m — all lengths in metres
- Pass width (e.g. 200) to zoom in and show more detail in the ASCII art
- The ASCII art is a sanity check for overall shape; it is not dimensionally precise. For exact positions and lengths use the components list or openrocket_component (action="read")
- Also returns mm-scaled CAD parameters ready for cadsmith: components (every _m field rewritten as _mm), derived (cg_x_mm, cp_x_mm, max_diameter_mm, body_tube_id_mm, motor_mount block), and handoff_notes
- Use this when handing off to the cadsmith subagent — it eliminates a whole class of m↔mm conversion errors and surfaces the fin-integration and coupler-sizing rules inline

Read the full file on GitHub · 262 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.

1mo ago First seen · 262 lines · 256 tokens per session scan A a7b5378a9fe7

Subscribe to this mod's changes

openrocket is an agent published in the GitHub repository ppak10/RocketSmith (21 stars, last pushed 5mo ago), licensed MIT. It adds 256 tokens to every session and 4,752 once invoked, about $0.0010 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.

Claude Code Scientific build123d gemini-cli-extension mcp openrocket prusaslicer

leakage-auditor

Specialized agent for detecting data leakage, train-test contamination, and temporal leakage in ML pipelines.

yeaight7/agent-powerups · 26 tokens

ml-experiment-reviewer

Evaluates ML experiment setups for rigorous baseline comparisons, proper metric tracking, and reproducibility.

yeaight7/agent-powerups · 24 tokens

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens