mass-calibration

mass-calibration is a skill for Claude Code from ppak10/RocketSmith. It costs 29 tokens per session (2,193 once invoked), scanned A, original, MIT.

A rocketry check that replaces OpenRocket’s estimated part weights with the measured weights of sliced 3D-printed parts. OpenRocket is software that simulates rocket flights and stability.

In plain words
What is it for?
Use it after slicing printed rocket parts, after changing print settings or material, and before final construction. It applies slicer weights to OpenRocket components and reruns the stability check.
Why use it?
Default material assumptions can make a rocket look stable in simulation even when the printed parts are much heavier or lighter. This helps verify stability using the parts’ expected real weights.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the rocketsmith plugin — 7 skills, 6 agents, 2 hooks shipped together

Good fit Use it after slicing printed rocket parts, after changing print settings or material, and before final construction. It applies slicer weights to OpenRocket components and reruns the stability check.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ppak10/rocketsmith/mass-calibration
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.

Any agent
npx skills add ppak10/RocketSmith --skill mass-calibration
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.

agentmods badge for mass-calibration

README.md
[![agentmods](https://agentmods.dev/badge/skills/ppak10/rocketsmith/mass-calibration.svg)](https://agentmods.dev/skills/ppak10/rocketsmith/mass-calibration)
Your own site
<a href="https://agentmods.dev/skills/ppak10/rocketsmith/mass-calibration"><img src="https://agentmods.dev/badge/skills/ppak10/rocketsmith/mass-calibration.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,193 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.02193
Opus 5 $0.00015 $0.01097
Sonnet 5 $0.00006 $0.00439
Haiku 4.5 $0.00003 $0.00219

Measured 8d ago against content hash 723fbeb5879d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mass-calibration 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.

skills/mass-calibration/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mass Calibration

Overview

OpenRocket assigns every component a mass based on its configured material (cardboard by default, typically ~680 kg/m³). Real printed parts are made of PLA or PETG and use variable wall/infill settings — their actual mass can differ from OpenRocket's estimate by 2–4×. A design that simulated stable with default material assumptions may be unstable once built.

Mass calibration closes the loop: slice each printed part, read the filament weight from the slicer, apply it back to the matching OpenRocket component as a mass override, and re-run the flight to confirm stability still holds.

Core principle: A design is not flight-ready until the flight has been re-verified against the real printed part weights, not the material defaults.

When to Use

  • cadsmith_run_script has produced STEP files AND prusaslicer_slice has produced gcode for at least one printed part
  • Before committing to a final build
  • After changing any print setting (infill, wall count, material) that would change part mass
  • When the user asks "will it still fly stable once printed?"

Preconditions

  1. The design has already passed an initial stability check in the 1.0–1.5 cal range with default masses. If not, run rocketsmith:stability-analysis first — calibrating on an already-unstable design obscures the root cause.
  2. <project_dir>/gui/component_tree.json exists (produced earlier by the design-for-additive-manufacturing skill or a sibling DFx skill). This is the authoritative mapping from printed parts back to OR components.
  3. Each printed part listed in the manifest has a sliced .gcode file with a filament_used_g reading. If any part is missing, slice it first.

Steps

1. Load the Component Tree

manifest = read_json("<project_dir>/gui/component_tree.json")

The two sections you care about are:

  • parts — each entry has a name, a gcode_path, and a derived_from list of the OR components the part was assembled from (post-fusion)
  • component_to_part_map — the inverse lookup: for every OR component in the .ork file, it tells you which printed part absorbed it, or that the component was "skipped" or "purchased" and does not need calibration

Read the full file on GitHub · 168 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 · 168 lines · 29 tokens per session scan A 723fbeb5879d

Subscribe to this mod's changes

mass-calibration is a skill published in the GitHub repository ppak10/RocketSmith (21 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 2,193 once invoked, about $0.0001 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 skills, from other repositories

aieng-cad-cae-copilot

MCP-first evidence workflow for AIENG CAD/CAE setup, solver preflight, approval-gated solver execution, and result extraction. Use when the user asks to inspect CAE readiness, patch setup, prepare/run CalculiX, or report stress/displacement evidence.

armpro24-blip/cad-cae-copilot · 65 tokens

aieng-closed-loop-copilot

MCP-first closed-loop CAD/CAE copilot skill for improving an existing solved design against explicit targets. Use when the user asks for bounded design iteration using editable CAD parameters, solver reruns, and evidence-backed comparison.

armpro24-blip/cad-cae-copilot · 54 tokens

alexandria

Reach for this when a research question needs cited sources across academic papers, public domain books, legal records, government archives, security advisories, news, or developer documentation. Alexandria is an MCP server backed by 152 public digital libraries; use it whenever an answer should point at real…

The-40-Thieves/alexandria-mcp · 71 tokens

cogp-shannon

A review method based on Claude Shannon's information theory, the study of how information travels through a channel. It examines signals, noise, compression, repetition, and feedback in communication.

ArchSightLabs/archsight-cognition · 49 tokens

cogp-darwin

A framework for analyzing how systems change through variation, competition, environmental pressure, and adaptation. It uses evolution as a way to examine survival and behavior over time.

ArchSightLabs/archsight-cognition · 44 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens