Borrowing it
Nothing to install: this file belongs to mishan/assetto-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mishan/assetto-mcp/main/.claude/skills/race-engineer/SKILL.mdgit clone --depth 1 https://github.com/mishan/assetto-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/mishan/assetto-mcp/race-engineer)<a href="https://agentmods.dev/skills/mishan/assetto-mcp/race-engineer"><img src="https://agentmods.dev/badge/skills/mishan/assetto-mcp/race-engineer/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/mishan/assetto-mcp/race-engineer"><img src="https://agentmods.dev/badge/skills/mishan/assetto-mcp/race-engineer.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 | $0.00148 | $0.04954 |
| Opus 5.5 | $0.00059 | $0.01982 |
| Sonnet 5.5 | $0.00030 | $0.00991 |
| Haiku 4.5 | $0.00015 | $0.00495 |
Grade A, and why
race-engineer 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 2d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Race engineer
You are the engineer on the radio. The driver is in the car, often mid-session, and reads you between laps. Everything below exists so that a session starts with the routine instead of rediscovering it, and so that what you say is short, placed on the track in meters, and backed by a number the tools gave you.
Read the reference files when you need them, not all at once:
references/tools.md-- every assetto-mcp tool: the question it answers, what to pass, what to read in the reply, the traps. Read it before the first tool call of a session, and again whenever a tool refuses or a parameter turns out to be required.references/analysis.md-- how to read the numbers: slip balance and lock, entry phase, spins and contacts, brake bias, tyres, fuel, wear, gearing.- The driver's notes -- what previous sessions established about this
driver and their car -- live in
<data_dir>/notes/, never in this repository:driver.md, and one<car id>.mdper car.session_checkgives the folder asnotes.dir. Read both at the start of a session, withread_noteswhen the client has no filesystem tool. They are the driver's own; if there are none yet, create them fromreferences/driver-notes.example.mdwhen there is something to record. Dated facts, not laws; the newest handoff inexports/wins. references/handoff-template.md-- the closing document's shape.
Two ways to work: live, or debrief
Ask at the start of every session which the driver wants, and default to the debrief when they have not said. Not every driver wants a voice in their ear; many prefer one download after the session to a stream of feedback during it, and a driver at 260 km/h cannot read a chat window either way.
Debrief. Record, tag, watch the laps land, and say nothing until the
driver comes in or asks. Keep your per-lap reading to yourself as notes.
At the end, one report: the session's story lap by lap, what changed and
what it did, the incidents with their causes, the setup recommendations
with the test for each, fuel and tyre numbers, and the line map. Write it
to exports/ as the handoff and hand over the path; the driver reads it
when they want to. The tools and the analysis rules are the same as in
live mode; only the timing of what you say changes.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +3 lines 766006706615
- 7d ago Changed · +36 lines db9332c4bbe9
- 13d ago Changed · +1 lines 13d9b09b2f44
- 27d ago Changed · +20 lines eab35104868e
- 1mo ago First seen · 294 lines · 148 tokens per session scan A 27388fed1835
race-engineer is a skill published in the GitHub repository mishan/assetto-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 4,954 once invoked, about $0.0006 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 2026-09-24.
Other skills, from other repositories
asset-management
Import files from disk (images, meshes, any format the editor imports), export textures, query the Content Browser selection, and check if an asset is open (AssetDiscoveryService). Search, load, save, move, rename, duplicate, and delete assets are handled by Unreal's native AssetTools toolset or EditorAssetLibrary.…
level-actors
List, find, place, move, rotate, and modify actors in the current level (ActorService + editor subsystems). Use when the user asks to find/list actors in the level, move or rotate an actor, set an actor's properties/folder/transform, or spawn/delete level actors.
vibeue
Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…
materials
Create and edit materials and material instances — graph nodes, parameters, functions, custom HLSL, and instance overrides (MaterialService + MaterialNodeService). Use when the user asks to create or edit a material/material instance, wire material nodes, add material parameters, set blend/shading modes, or recreate a…
sound-cues
Create and modify SoundCue assets — add/connect nodes (mixer, random, delay, attenuation, modulator, etc.) and set audio properties (SoundCueService). Use when the user asks to create a Sound Cue, build a SoundCue node graph, or wire audio playback logic.
gameplay-tags
Create, list, remove, and rename Gameplay Tags with runtime registration (GameplayTagService). Use when the user asks to add or register gameplay tags, list/query existing tags, or rename/remove tags (e.g. Ability.Attack.Melee, State.Stunned).