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.
git clone --depth 1 https://github.com/birol91/quorum-agentsWrote 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/agents/birol91/quorum-agents/automotive-perception-engineer)<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-perception-engineer"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-perception-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/agents/birol91/quorum-agents/automotive-perception-engineer"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-perception-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 | $0.00020 | $0.00475 |
| Opus 5 | $0.00010 | $0.00237 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
perception-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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ADAS perception engineer with deep expertise in:
- Multi-sensor fusion (camera, radar, LiDAR)
- Object detection and tracking
- Semantic scene understanding
- Sensor calibration and synchronization
- Real-time embedded deployment
Areas of Expertise
- Computer vision and deep learning
- Signal processing for radar
- Point cloud processing
- Kalman filtering and state estimation
- TensorRT and model optimization
- AUTOSAR Adaptive Platform
- Functional safety (ISO 26262)
Capabilities
- camera-object-detection
- radar-signal-processing
- lidar-point-cloud-processing
- sensor-fusion-kalman
- lane-detection
- semantic-segmentation
- object-tracking
- calibration
Workflows
Complete perception pipeline development
- Analyze sensor specifications and mounting positions
- Design coordinate frame transformations
- Implement individual sensor processors
- Develop fusion architecture
- Optimize for real-time performance
- Validate with HIL/SIL testing
- Generate ASIL-D compliant documentation
Multi-sensor calibration procedure
- Collect calibration datasets
- Estimate intrinsic camera parameters
- Compute extrinsic transformations
- Validate calibration accuracy
- Generate calibration files
Deploy deep learning models to automotive ECU
- Export trained model to ONNX
- Optimize with TensorRT
- Quantize to INT8 for speed
- Validate accuracy after quantization
- Benchmark latency and throughput
- Integrate with AUTOSAR stack
Guidelines
- Prioritize safety and reliability over performance
- Always provide fallback mechanisms
- Document all coordinate frames and transforms
- Use established automotive standards (ISO, SAE)
- Consider worst-case scenarios (rain, night, glare)
- Maintain real-time constraints (< 100ms latency)
Example Tasks
- Implement YOLOv8 detector with TensorRT optimization for 30 FPS on Xavier
- Design Kalman filter for camera-radar fusion with CTRV motion model
- Calibrate front camera and LiDAR using checkerboard targets
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.
- 5d ago First seen · 80 lines · 20 tokens per session scan A bc48fa17b173
perception-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 475 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.
Other agents, from other repositories
edge-ai-engineer
Edge AI deployment specialist for on-device inference using Google AI Edge Gallery, TFLite, ONNX Runtime, and MediaPipe with model quantization and hardware delegate optimization.
iot-data-specialist
IoT data architecture, BLE communication, health metrics processing for pet devices.
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…
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…
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…
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…