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.
npx skills add KevinInoCol/coppeliasim-mcp --skill robo-diferencial-e-sensoresgit clone --depth 1 https://github.com/KevinInoCol/coppeliasim-mcpWrote 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.
[](https://agentmods.dev/skills/kevininocol/coppeliasim-mcp/robo-diferencial-e-sensores)<a href="https://agentmods.dev/skills/kevininocol/coppeliasim-mcp/robo-diferencial-e-sensores"><img src="https://agentmods.dev/badge/skills/kevininocol/coppeliasim-mcp/robo-diferencial-e-sensores/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.
<a href="https://agentmods.dev/skills/kevininocol/coppeliasim-mcp/robo-diferencial-e-sensores"><img src="https://agentmods.dev/badge/skills/kevininocol/coppeliasim-mcp/robo-diferencial-e-sensores.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00118 | $0.01376 |
| Opus 5 | $0.00059 | $0.00688 |
| Sonnet 5 | $0.00024 | $0.00275 |
| Haiku 4.5 | $0.00012 | $0.00138 |
Grade A, and why
robo-diferencial-e-sensores 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Robô diferencial e sensores
Cada armadilha desta página custa horas. Todas foram medidas num robô que funciona.
Juntas: o eixo e o modo de controle
Uma junta atua ao longo do próprio +Z. Para uma roda que impulsiona para
+X, o eixo precisa ficar sobre Y, o que significa girar a junta inteira (-pi/2
em torno de X). Não é parâmetro da chamada: é a orientação do objeto.
Uma junta sem modo de controle é surda. Você manda velocidade e nada
acontece até definir dynCtrlMode, que é uma propriedade, não um argumento
da criação. No modo de velocidade o valor é 4 (não 2, que é o que se supõe):
sim.setInt32Property(junta, "dynCtrlMode", sim.jointdynctrl_velocity)
sim.setJointTargetVelocity(junta, 3.0)
A tool crear_junta do MCP faz as duas coisas por você.
Atrito: o Bullet lê frictionOld
O Bullet 2.7, que é o motor padrão, obedece bullet.frictionOld, não
bullet.friction. O CoppeliaSim expõe os dois e qual manda depende da versão
do Bullet escolhida na cena. Definir só bullet.friction não faz absolutamente
nada.
Medido num diferencial real: uma roda boba com o atrito velho em 1 arrastou o robô para 87% da distância em reta e 51% do giro, patinando em vez de pivotar sobre o eixo motriz. Escreva sempre os dois.
Roda boba: atrito bem baixo. Rodas motrizes: atrito alto.
Massa e inércia
computeMassAndInertia só funciona com formas convexas. Não funda o chassi
com a carga e depois chame: deixe cada peça convexa separada e calcule a massa
de cada uma.
Sem massa razoável, um robô leve com rodas finas treme ou sai voando.
Rodas finas
Rodas de 1 cm de espessura são pouquíssimo para o Bullet: o contato é quase uma linha e o robô treme. Compense com atrito alto e massa suficiente. Se o robô vibra parado, trace a altura do chassi ao longo do tempo — se oscila, é isso.
Grupos de colisão
As peças do robô não devem colidir entre si, mas devem colidir com o mundo. A
máscara de respondable resolve as duas coisas: os 8 bits baixos dizem com quem
colide dentro da mesma árvore e os 8 altos com o resto. Com 0xFF00 as peças do
robô se ignoram — acabaram os tremores — e continuam batendo no chão e nos
obstáculos.
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.
- 11d ago First seen · 116 lines · 118 tokens per session scan A 8881897b04f4
robo-diferencial-e-sensores is a skill published in the GitHub repository KevinInoCol/coppeliasim-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 118 tokens to every session and 1,376 once invoked, about $0.0006 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.
Other skills, from other repositories
tiaportal-mcp
A skill for controlling Siemens TIA Portal, the engineering software used to configure Siemens PLCs and HMIs. It works through an MCP server, a tool connection that lets an agent inspect and change projects.
asset-management
Manage ServiceNow hardware assets, software licenses, and lifecycle states on almhardware/almlicense — license allocation, CMDB-to-asset linking, warranty tracking, inventory aggregation (HAM/SAM).
kernelcad-assemblies
Multi-part assemblies — assembly(), parts, connectors, 7 mate types, fixed and revolute joints, .model()/.solvedModel(). Use for any model with two or more mechanical parts that need joint metadata.
kernelcad-kinematic
Use when verifying whether a moving assembly is buildable — sampled-pose collision sweeps across joint ranges, IK reachability for end-effector targets, mounting-hole fastener consistency, and static-load capacity on cantilever-shaped parts. Loads alongside kernelcad-authoring to gate design-time mechanism feasibility.
kernelcad-parts
Bundled parts catalog — discover, fetch, and mate standard fasteners, bearings, motors, headers, and connectors. Use whenever the model needs an off-the-shelf component instead of hand-modeled placeholder geometry.
use-the-available-kernel
Hard rules for which kernelCAD primitive to reach for when authoring from a reference photo. The from-reference loop fails most often because the author defaults to easy primitives and skips ones that exist. Read before writing any geometry.