beamng-mods
Skill2 starsChanged 7 months agoMITView on GitHub
Build and debug BeamNG.drive and BeamMP mods, resources, and server plugins using Lua. Use this skill whenever the user mentions BeamNG modding, BeamMP, `Resources/Server`, `Resources/Client`, `modScript.lua`, `lua/ge/extensions`, `extensions.load`, `MP.RegisterEvent`, `AddEventHandler`, client/server event wiring, custom vehicles, gameplay scripts, or BeamNG Lua hooks.
In this repository26 other files it gives its agents.
- other/AGENTS.mdAGENTS.md
- bootstrap-vueSkill
- charmbraceletSkill
- depsdotdevSkill
- find-domainSkill
- github-cliSkill
- go-cobraSkill
- goreleaserSkill
- go-viperSkill
- kasettoSkill
- laravel-actionsSkill
- lefthookSkill
- miseSkill
- pelican-panel-pluginsSkill
- php-monorepo-builderSkill
- php-saloonSkill
- prd-todo-slicerSkill
- prd-to-kandev-tasksSkill
- qodo-mergeSkill
- release-pleaseSkill
- rewrite-in-goSkill
- shieldsioSkill
- skill-researcherSkill
- skill-scoutSkill
- taskfileSkill
- website-visual-testingSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Keep responses concise and implementation-first.
- Distinctive: line 25
If target is unclear, ask one short clarifying question.
- Distinctive: line 50
Use JSON payloads for client/server boundaries and validate inputs.
- Distinctive: line 51
Keep event handlers short.
- Distinctive: line 52
Prefer one small, testable feature per iteration.
- Distinctive: line 53
If any local stubs are provided, treat them as helper hints only.
- Distinctive: line 57
When implementing/scaffolding, include:
- Distinctive: line 65
Prefer official docs first:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
BeamNG + BeamMP Modding
Build, scaffold, and debug:
- BeamMP server plugins
- BeamMP client mods (
modScript.lua+ GE extension) - BeamNG Lua extensions (
common/ge/vehicle)
Keep responses concise and implementation-first. Prefer small working patches.
First Decision
Choose one target before writing code:
beammp-serverbeammp-clientbeamng-only
If target is unclear, ask one short clarifying question.
Progressive Loading
Load only what is needed.
For beammp-server:
references/layouts.mdreferences/beammp-server-api.mdexamples/beammp-server-main.lua(when scaffolding code)
For beammp-client:
references/layouts.mdreferences/beammp-client-api.mdexamples/beammp-client-extension.luaexamples/modScript.lua
For beamng-only:
references/layouts.mdreferences/beamng-extension-api.mdexamples/beamng-ge-extension.lua(or adapt for common/vehicle VM)
Core Rules
- Namespace custom events as
pluginName:eventName. - Use JSON payloads for client/server boundaries and validate inputs.
- Keep event handlers short; avoid long blocking loops/sleeps.
- Prefer one small, testable feature per iteration.
- If any local stubs are provided, treat them as helper hints only; prefer official docs on conflicts.
Output Format
When implementing/scaffolding, include:
- Target type (
beammp-server,beammp-client, orbeamng-only) - Final file tree
- Code changes
- Quick test steps
Sources
Prefer official docs first:
- https://docs.beammp.com/scripting/server/latest-server-reference/
- https://docs.beammp.com/scripting/mod-reference/
- https://docs.beammp.com/guides/mod-creation/server/getting-started/
- https://docs.beamng.com/modding/programming/extensions/
- https://docs.beamng.com/modding/programming/virtualmachines/
Optional local sources (only if present in the current repo):
- BeamMP/BeamNG Lua stubs
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

