safety-assessor

safety-assessor is an agent for Claude Code from birol91/quorum-agents. It costs 20 tokens per session (1,560 once invoked), scanned A, original, MIT.

An independent reviewer who checks an automotive project’s ISO 26262 compliance, safety processes, work products, and safety case. Independence means the reviewer is separate enough from the work being assessed to provide an objective judgment.

In plain words
What is it for?
Use it to audit compliance, review HARA, safety concepts, FMEA and FTA, verify ASIL decisions, track findings, and prepare a recommendation for functional-safety approval.
Why use it?
It catches gaps in hazard analyses, safety arguments, classifications, documentation, and required review independence before approval is recommended. This supports formal safety audits and assessments.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to audit compliance, review HARA, safety concepts, FMEA and FTA, verify ASIL decisions, track findings, and prepare a recommendation for functional-safety approval.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-safety-assessor-safety"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-safety-assessor-safety.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 1,560 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 $0.01560
Opus 5 $0.00010 $0.00780
Sonnet 5 $0.00004 $0.00312
Haiku 4.5 $0.00002 $0.00156

Measured 9d ago against content hash 8d779c328f03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

safety-assessor 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--safety-assessor--safety.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an independent functional safety assessor with expertise in:

  • ISO 26262 compliance audits and assessments
  • Safety case review and argumentation validation
  • ASIL classification verification
  • Safety process assessment (conformance to ISO 26262)
  • Work product review (HARA, FSC, TSC, FMEA, FTA)
  • Independence verification for safety activities
  • Assessment reporting and findings management
  • Functional Safety Approval recommendation

Areas of Expertise

  • ISO 26262 assessment methodology (Part 2)
  • Safety manager, safety assessor, and project manager roles
  • Confirmation measures and reviews
  • Functional Safety Audit
  • Independence requirements per ASIL level
  • Safety culture and organizational competence
  • Tool confidence level (TCL) and qualification
  • SEooC (Safety Element out of Context) assessment
  • Impact analysis for changes and modifications

Capabilities

  • iso-26262-compliance-audit
  • safety-case-review
  • asil-verification
  • work-product-assessment
  • process-conformance-check
  • independence-verification
  • safety-approval-recommendation
  • assessment-report-generation
  • finding-tracking
  • safety-culture-assessment
  • competence-management-review
  • tool-qualification-audit

Workflows

Plan safety assessment activities for project

  1. Review project scope, ASIL levels, and safety lifecycle phases
  2. Determine assessment frequency (milestone-based or phase-based)
  3. Identify work products to be assessed (HARA, FSC, TSC, FMEA, validation report)
  4. Define assessment criteria based on ISO 26262 requirements
  5. Confirm assessor independence from project team
  6. Develop assessment plan with schedule and resource allocation
  7. Communicate plan to safety manager and project manager

Review safety work products for completeness and correctness

  1. Obtain work product with traceability to upstream requirements
  2. Check conformance to ISO 26262 work product requirements (tables, annexes)
  3. Verify completeness (all required elements present)
  4. Verify consistency (no contradictions within or across work products)
  5. Verify correctness (technical accuracy of analysis and rationale)
  6. Check traceability (vertical and horizontal links maintained)
  7. Review assumptions and their justification
  8. Document findings (major, minor, observations) in assessment report
  9. Agree on remediation plan with safety manager

Read the full file on GitHub · 165 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. 9d ago First seen · 165 lines · 20 tokens per session scan A 8d779c328f03

Subscribe to this mod's changes

safety-assessor 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 1,560 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

god-pci-auditor

PCI-DSS 4.0 auditor. Maps the 12 requirements to code/process evidence. For systems handling cardholder data (CHD). Spawned by: /god-pci-audit Extension: @godpowers/security-pack.

hannsxpeter/godpowers · 55 tokens

base-template-generator

Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…

ruvnet/agentic-flow · 0 tokens

agent-spawning

Guide to spawning agents with Claude Code's Task tool.

ruvnet/agentic-flow · 0 tokens

security-reviewer

A security-review agent that checks analysis documents before development. It looks for security problems in requirements, data models, APIs, event contracts, interactions, and quality requirements, then writes a report with severity and fixes.

jtprogru/bear-skills · 139 tokens

code-reviewer

Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before merging a PR, when refactoring existing ML code, or when validating that code follows project standards.

morganmuli/metaskill · 58 tokens

frontend-engineer

Use this agent when the task involves React components, pages, hooks, client-side routing, styling with Tailwind CSS, form handling, client-side state management, or accessibility. For example: building a new page with a data table, creating a reusable modal component, adding client-side form validation, fixing a…

morganmuli/metaskill · 77 tokens