differential-robot-and-sensors

differential-robot-and-sensors is a skill for Claude Code from KevinInoCol/coppeliasim-mcp. It costs 95 tokens per session (1,205 once invoked), scanned A, original, MIT.

A guide to building a two-wheeled robot and proximity sensors in CoppeliaSim. It explains wheel joints, physics settings, collisions, and what sensors can see.

In plain words
What is it for?
Use it when adding wheels, joints, friction, mass, collision settings, or proximity sensors to a mobile robot.
Why use it?
It addresses common reasons a simulated robot does not move, turns poorly, collides incorrectly, or fails to detect objects.

Skill for Claude Code

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

Part of the coppeliasim plugin — 9 skills, 1 MCP server shipped together

Good fit Use it when adding wheels, joints, friction, mass, collision settings, or proximity sensors to a mobile robot.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors
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 KevinInoCol/coppeliasim-mcp --skill differential-robot-and-sensors
Clone the repo
git clone --depth 1 https://github.com/KevinInoCol/coppeliasim-mcp

Made for: Claude Code.

Or install coppeliasim, the plugin that ships this one along with the rest of its 9 skills, 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 differential-robot-and-sensors

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors/github.svg)](https://agentmods.dev/skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors)
Your own site
<a href="https://agentmods.dev/skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors"><img src="https://agentmods.dev/badge/skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors/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.

agentmods 80×15 button for differential-robot-and-sensors

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors"><img src="https://agentmods.dev/badge/skills/kevininocol/coppeliasim-mcp/differential-robot-and-sensors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,205 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 $0.00095 $0.01205
Opus 5 $0.00048 $0.00602
Sonnet 5 $0.00019 $0.00241
Haiku 4.5 $0.00010 $0.00120

Measured 11d ago against content hash bee0e597f45d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

differential-robot-and-sensors 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 11d 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/differential-robot-and-sensors/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Differential drive robot and sensors

Every trap on this page costs hours. All of them were measured on a robot that works.

Joints: axis and control mode

A joint acts along its own +Z. For a wheel driving toward +X, the axis must lie along Y, which means rotating the whole joint (-pi/2 about X). It is not a call parameter: it is the object's orientation.

A joint with no control mode is deaf. Send it a velocity and nothing happens until dynCtrlMode is set — a property, not an argument of the creation call. For velocity control the value is 4 (not 2, which is what you would guess):

sim.setInt32Property(joint, "dynCtrlMode", sim.jointdynctrl_velocity)
sim.setJointTargetVelocity(joint, 3.0)

The MCP's crear_junta tool does both for you.

Friction: Bullet reads frictionOld

Bullet 2.7, the default engine, obeys bullet.frictionOld, not bullet.friction. CoppeliaSim exposes both and which one wins depends on the Bullet version selected in the scene. Setting only bullet.friction does nothing at all.

Measured on a real differential drive: a caster left at old-friction 1 dragged the robot down to 87% of its straight-line distance and 51% of its turn rate, skid-steering instead of pivoting on its drive axle. Always write both.

Caster: very low friction. Drive wheels: high friction.

Mass and inertia

computeMassAndInertia only works on convex shapes. Do not merge the chassis with the payload and then call it: keep each piece convex on its own and compute each mass separately.

Without sensible mass, a light robot on thin wheels jitters or gets flung.

Thin wheels

Wheels 1 cm thick are very little for Bullet: the contact is almost a line and the robot shakes. Compensate with high friction and enough mass. If the robot vibrates while standing still, trace the chassis height over time — if it oscillates, this is why.

Collision groups

The robot's parts must not collide with each other, but must collide with the world. The respondable mask does both at once: the low 8 bits say who it hits within the same tree, the high 8 bits who it hits outside. With 0xFF00 the robot's parts ignore each other — no more jitter — and still hit the floor and the obstacles.

Read the full file on GitHub · 117 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. 11d ago First seen · 117 lines · 95 tokens per session scan A bee0e597f45d

Subscribe to this mod's changes

differential-robot-and-sensors is a skill published in the GitHub repository KevinInoCol/coppeliasim-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 95 tokens to every session and 1,205 once invoked, about $0.0005 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

kernelcad-sdformat

Export multi-part assemblies to SDFormat — closed kinematic loops, native ball joints, solved per-link poses, per-link inertial/visual/collision with mesh files. Use when the downstream simulator ingests SDFormat directly or the assembly needs closed-loop / native-spherical-joint support.

w1ne/kernelCAD-web · 64 tokens

okx-cex-portfolio

This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…

okx/agent-trade-kit · 236 tokens

isuzu-unity-cli

Control Unity Editor from the CLI with the isuzu-unity-cli command. Execute C# code, browse scene hierarchy, inspect/modify GameObjects, capture screenshots, read console logs, check compile status, control play mode, and execute menu items. Use when: user wants to interact with Unity Editor programmatically, run C#…

isuzu-shiranui/UnityMCP · 97 tokens

hz-unity-meta-movement-sdk-retargeting

Set up and tweak Meta Movement SDK (MSDK) retargeting for a character model. Use this whenever the user wants to retarget a humanoid FBX/prefab for Meta Quest body tracking, generate a retargeting config, or hand-edit the resulting .json (fix known-joint mappings, exclude joints from auto-mapping, rename target…

meta-quest/agentic-tools · 182 tokens

hz-unity-face-tracking

Drive ARKit-blendshape-rigged head/face models in Unity with the wearer's facial expressions on Meta Quest via Meta Movement SDK (face tracking + A2E). Use when a user has an FBX with the 52 ARKit blendshapes (any prefix, L/R suffixes) and wants it to animate from face tracking on Quest Pro / Quest 3 / Quest 3S.

meta-quest/agentic-tools · 92 tokens

metavr-cli

Provides the complete metavr (Meta VR CLI) reference for Meta Quest and Horizon OS development — installation, device setup, command discovery, MCP server mode, documentation search, app deployment, device testing setup, audio control, screenshots, and performance analysis. Use when the user needs to install metavr…

meta-quest/agentic-tools · 85 tokens