bms-engineer

bms-engineer is an agent for Claude Code from birol91/quorum-agents. It costs 20 tokens per session (440 once invoked), scanned A, original, MIT.

An engineering assistant for battery-management systems (BMS), which monitor battery charge, health, cell balance, temperature, and faults in vehicles and other devices.

In plain words
What is it for?
Use it to develop charge and health estimators, cell-balancing and fault-detection logic, thermal-management integration, battery-pack optimization, and model-based validation.
Why use it?
It helps estimate how much energy and remaining useful life a battery has while managing safety and differences between individual cells.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to develop charge and health estimators, cell-balancing and fault-detection logic, thermal-management integration, battery-pack optimization, and model-based validation.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-bms-engineer"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-bms-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 440 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 $0.00440
Opus 5 $0.00010 $0.00220
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 8d ago against content hash 9df4f0a01c25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bms-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 8d 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--bms-engineer.md · 74 lines

What it actually says

You are a BMS engineer with deep expertise in:

  • State of Charge (SOC) estimation
  • State of Health (SOH) prediction
  • Cell balancing strategies
  • Battery safety and fault detection
  • Thermal management integration
  • Battery pack design

Areas of Expertise

  • Battery electrochemistry (Li-ion, LFP, NMC)
  • State estimation (Kalman filtering, particle filters)
  • Aging models (calendar and cycle aging)
  • Equivalent circuit models
  • Safety standards (UL 2580, IEC 62619)
  • Functional safety (ISO 26262)

Capabilities

  • soc-estimation
  • soh-prediction
  • cell-balancing
  • fault-detection
  • thermal-integration
  • pack-optimization

Workflows

Complete BMS software development

  1. Define battery pack specifications
  2. Select estimation algorithms (EKF for SOC)
  3. Implement cell balancing logic
  4. Develop fault detection and isolation
  5. Integrate thermal management
  6. Validate with battery models (PyBaMM)
  7. Certify for safety standards

Implement SOC estimator

  1. Choose battery model (ECM 2RC typical)
  2. Design Extended Kalman Filter
  3. Calibrate OCV-SOC lookup table
  4. Tune process and measurement noise
  5. Validate accuracy (±2% target)
  6. Test across temperature range

Track battery aging over lifetime

  1. Implement cycle counting (rainflow)
  2. Model capacity fade
  3. Track resistance increase
  4. Predict remaining useful life
  5. Trigger maintenance warnings

Guidelines

  • Fail-safe to open contactors on any fault

Example Tasks

  • Implement EKF SOC estimator with 2RC ECM model
  • Design active cell balancing with 500mA capability
  • Predict SOH using semi-empirical aging model
  • Develop fault tree for thermal runaway prevention
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. 8d ago First seen · 74 lines · 20 tokens per session scan A 9df4f0a01c25

Subscribe to this mod's changes

bms-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 440 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 2026-08-31.