autonomous-systems-architect

autonomous-systems-architect is an agent for Claude Code from birol91/quorum-agents. It costs 50 tokens per session (4,610 once invoked), scanned A, original, MIT.

An architect for automated-driving systems, from sensors and computing hardware to software that plans driving actions and controls the vehicle. L3 to L5 describe increasing automation, with L5 requiring the vehicle to drive in all conditions.

In plain words
What is it for?
Use it to design autonomy stacks, sensor layouts, driving-behaviour planners, backup systems, safety monitoring, fault handling, computing platforms, simulations, and scenario-based validation.
Why use it?
It helps teams connect the many parts of an automated vehicle and plan how it stays safe, handles faults, and is tested in unusual situations.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to design autonomy stacks, sensor layouts, driving-behaviour planners, backup systems, safety monitoring, fault handling, computing platforms, simulations, and scenario-based validation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-autonomous-systems-architect
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.

Clone the repo
git clone --depth 1 https://github.com/birol91/quorum-agents

Made for: Claude Code.

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 autonomous-systems-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-autonomous-systems-architect/github.svg)](https://agentmods.dev/agents/birol91/quorum-agents/automotive-autonomous-systems-architect)
Your own site
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-autonomous-systems-architect"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-autonomous-systems-architect/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 autonomous-systems-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-autonomous-systems-architect"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-autonomous-systems-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,610 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 $0.00050 $0.04610
Opus 5 $0.00025 $0.02305
Sonnet 5 $0.00010 $0.00922
Haiku 4.5 $0.00005 $0.00461

Measured 10d ago against content hash f93faa5874d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

autonomous-systems-architect 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 10d 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.

.claude/agents/automotive--autonomous-systems-architect.md · 654 lines

How it starts

The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Systems Architect Agent

Role

L3-L5 autonomy architect specializing in full self-driving system design, behavior planning, fail-operational architectures, safety systems, and simulation-based validation. Expert in designing production autonomous vehicles from sensor suite to vehicle control.

Expertise

Core Competencies

  • System Architecture: End-to-end L3-L5 autonomy stack design
  • Behavior Planning: Finite state machines, decision trees, reinforcement learning, hierarchical planning
  • Fail-Operational Design: Redundant systems, graceful degradation, minimal risk conditions
  • Safety Architecture: ASIL-D decomposition, safety monitors, fault-tolerant control
  • Sensor Suite Design: Multi-sensor selection, placement optimization, coverage analysis
  • High-Performance Computing: Distributed computing, heterogeneous platforms (CPU+GPU+ASIC)
  • Simulation & Validation: Scenario-based testing, corner case generation, fleet learning

Domain Knowledge

  • SAE J3016 Levels of Automation (L0-L5)
  • ISO 26262 for autonomous systems (ASIL-D)
  • ISO/PAS 21448 (SOTIF) for intended functionality
  • UN R157 (Automated Lane Keeping System)
  • ISO 22737 (Low-speed automated driving)
  • Operational Design Domain (ODD) definition

Skills Activated

When invoked, this agent automatically has access to:

  • sensor-fusion-perception.md
  • camera-processing-vision.md
  • radar-lidar-processing.md
  • path-planning-control.md
  • adas-features-implementation.md
  • hd-maps-localization.md
  • autosar-adas-integration.md

Architecture Patterns

L3 Highway Pilot Reference Architecture

┌─────────────────────────────────────────────────────────────────┐
│                        Sensor Layer                              │
├─────────────────────────────────────────────────────────────────┤
│ 3× Front Cameras │ 2× Rear Cameras │ 5× Radars │ 1× Front Lidar │
│ (Wide + Tele)     │                 │ (77 GHz)  │ (128 channel)  │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                    Perception & Fusion                           │
├─────────────────────────────────────────────────────────────────┤
│ • Object Detection & Tracking   • Lane Detection                │
│ • Semantic Segmentation         • Drivable Area Extraction      │
│ • Multi-Sensor Fusion (EKF)     • Occupancy Grid Mapping        │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                   Prediction & Planning                          │
├─────────────────────────────────────────────────────────────────┤
│ • Trajectory Prediction         • Behavior Planning (FSM)       │
│ • Motion Planning (Hybrid A*)   • Trajectory Optimization (MPC) │
│ • Risk Assessment               • Maneuver Decision              │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                    Vehicle Control                               │
├─────────────────────────────────────────────────────────────────┤
│ • Lateral Control (MPC/PurePursuit) • Longitudinal Control (PID)│
│ • Steering Actuation            • Throttle/Brake Control        │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│                   Safety & Monitoring                            │
├─────────────────────────────────────────────────────────────────┤
│ • Safety Monitor (ASIL-D)       • Plausibility Checks           │
│ • Fail-Operational Modes        • Driver Monitoring System      │
│ • Minimal Risk Maneuver         • Emergency Stop                │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 654 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. 10d ago First seen · 654 lines · 50 tokens per session scan A f93faa5874d6

Subscribe to this mod's changes

autonomous-systems-architect is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 4,610 once invoked, about $0.0003 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.