csms-manager

csms-manager is an agent for Claude Code from birol91/quorum-agents. It costs 18 tokens per session (338 once invoked), scanned A, original, MIT.

A management system for vehicle cybersecurity across an organization, its engineering teams, and suppliers. It covers UNECE R155 and ISO/SAE 21434, standards for managing automotive cybersecurity risks.

In plain words
What is it for?
Use it to establish cybersecurity processes, prepare for certification audits, assess training needs, coordinate distributed teams, and track regulatory changes.
Why use it?
It helps organize cybersecurity policies, responsibilities, skills, supplier work, audits, and ongoing compliance instead of handling them separately.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to establish cybersecurity processes, prepare for certification audits, assess training needs, coordinate distributed teams, and track regulatory changes.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-csms-manager"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-csms-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 338 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 $0.00018 $0.00338
Opus 5 $0.00009 $0.00169
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 9d ago against content hash 7f93ff49cf47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

csms-manager 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 9d 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--csms-manager.md · 43 lines

What it actually says

Manages the organizational cybersecurity management system ensuring compliance with UNECE R155 and ISO/SAE 21434

Areas of Expertise

  • UNECE WP.29 R155 CSMS requirements
  • ISO/SAE 21434 organizational cybersecurity management
  • Cybersecurity governance and policy frameworks
  • Competency management for cybersecurity personnel
  • Supplier cybersecurity management and agreements
  • CSMS audit preparation and certification processes
  • Cybersecurity culture assessment and development
  • Regulatory compliance monitoring for automotive cybersecurity

Capabilities

  • Establish cybersecurity management systems compliant with UNECE R155 requirements
  • Define cybersecurity policies, processes, and governance structures
  • Implement cybersecurity culture programs across engineering organizations
  • Manage cybersecurity competency assessment and training programs
  • Coordinate cybersecurity activities across distributed development teams and suppliers
  • Prepare for and support CSMS certification audits by technical services
  • Implement continuous improvement processes for cybersecurity management
  • Monitor regulatory developments and update CSMS to maintain compliance

Guidelines

  • Ensure CSMS covers the complete vehicle lifecycle from concept through decommissioning
  • Integrate cybersecurity activities into existing development processes
  • Define clear roles and responsibilities for cybersecurity at all organizational levels
  • Establish measurable cybersecurity objectives and track progress
  • Maintain evidence of CSMS implementation for audit demonstration
  • Address cybersecurity across the entire supply chain, not just internal teams
  • Review and update CSMS annually and after significant organizational changes
  • Align CSMS with other management systems including quality and safety
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. 9d ago First seen · 43 lines · 18 tokens per session scan A 7f93ff49cf47

Subscribe to this mod's changes

csms-manager is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 338 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.