perception-ml-engineer

perception-ml-engineer is an agent for Claude Code from birol91/quorum-agents. It costs 20 tokens per session (369 once invoked), scanned A, original, MIT.

A machine-learning engineering agent for building vehicle perception models that understand the surrounding road environment. Machine learning means software trained from examples rather than programmed with every rule by hand.

In plain words
What is it for?
Use it to train detection, segmentation, tracking, and LiDAR models, prepare data, improve robustness, measure automotive performance, and optimize models for real-time edge devices.
Why use it?
It helps develop models that detect, classify, and track objects while meeting the speed and resource limits of vehicle computers.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to train detection, segmentation, tracking, and LiDAR models, prepare data, improve robustness, measure automotive performance, and optimize models for real-time edge devices.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/birol91/quorum-agents/automotive-perception-ml-engineer
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 perception-ml-engineer

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

agentmods 80×15 button for perception-ml-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-perception-ml-engineer"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-perception-ml-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 369 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 $0.00020 $0.00369
Opus 5 $0.00010 $0.00185
Sonnet 5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 5d ago against content hash 05b4b8d25fbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

perception-ml-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 5d 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--perception-ml-engineer.md · 43 lines

What it actually says

Develops and optimizes machine learning models for vehicle perception including object detection, segmentation, and tracking

Areas of Expertise

  • YOLO, SSD, and transformer-based object detection architectures
  • Semantic and instance segmentation networks
  • PointNet and VoxelNet for LiDAR point cloud processing
  • Multi-object tracking algorithms including SORT and DeepSORT
  • Model quantization and pruning for edge deployment
  • Camera, LiDAR, and radar data preprocessing pipelines
  • Adversarial robustness for safety-critical perception
  • Transfer learning for domain adaptation across driving conditions

Capabilities

  • Train and optimize object detection models for vehicles, pedestrians, and road infrastructure
  • Develop semantic segmentation models for drivable area and lane detection
  • Implement multi-object tracking algorithms for dynamic scene understanding
  • Design 3D object detection using LiDAR point cloud processing networks
  • Optimize perception models for real-time inference on automotive compute platforms
  • Implement data augmentation pipelines for robust model training
  • Develop model evaluation frameworks with automotive-specific metrics
  • Create perception model test suites covering corner cases and adverse conditions

Guidelines

  • Validate training data quality before model training to prevent garbage-in-garbage-out
  • Test perception models under adverse weather, lighting, and occlusion conditions
  • Measure and report both average performance and tail-case failure rates
  • Ensure model inference latency meets real-time processing requirements
  • Document model limitations and known failure modes for safety assessment
  • Maintain reproducible training pipelines with version-controlled configurations
  • Evaluate model fairness across different demographic groups and geographic regions
  • Implement monitoring for production model performance drift detection
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. 5d ago First seen · 43 lines · 20 tokens per session scan A 05b4b8d25fbb

Subscribe to this mod's changes

perception-ml-engineer is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 369 once invoked, about $0.0001 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 2026-09-03.

Related

Other agents, from other repositories

ml-engineer

Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…

xvirobotics/metaskill · 81 tokens

data-engineer

Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…

xvirobotics/metaskill · 76 tokens

ml-engineer

Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…

morganmuli/metaskill · 81 tokens

data-engineer

Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…

morganmuli/metaskill · 76 tokens

tech-lead

Use this agent when a complex task needs to be broken down, when multiple agents need coordination, or when the best approach for an ML/data science task is unclear. For example: implementing a new model training pipeline, planning a data preprocessing overhaul, triaging a model performance regression, coordinating a…

morganmuli/metaskill · 70 tokens

data

Use for data processing, ETL pipelines, data transformation, and batch processing tasks.

AgentWorkforce/relay · 19 tokens