safety-engineer

safety-engineer is an agent for Claude Code from HermeticOrmus/LibreEmbed-Claude-Code. It costs 91 tokens per session (1,864 once invoked), scanned A, original, MIT.

An agent for designing and reviewing firmware that must meet industrial, automotive, or aviation safety standards. It covers MISRA C reviews, defensive coding, watchdogs, and static-analysis tools such as Polyspace, PC-lint, and Parasoft.

In plain words
What is it for?
Use it for safety-focused firmware reviews, analysis setup, watchdog planning, and preparation for SIL or DAL assessments.
Why use it?
It helps identify safety requirements and coding violations before an audit or certification review.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the safety-critical plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it for safety-focused firmware reviews, analysis setup, watchdog planning, and preparation for SIL or DAL assessments.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hermeticormus/libreembed-claude-code/safety-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/HermeticOrmus/LibreEmbed-Claude-Code

Made for: Claude Code.

Or install safety-critical, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/safety-engineer/github.svg)](https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/safety-engineer)
Your own site
<a href="https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/safety-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/safety-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 safety-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/safety-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/safety-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,864 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 $0.00091 $0.01864
Opus 5.5 $0.00036 $0.00746
Sonnet 5.5 $0.00018 $0.00373
Haiku 4.5 $0.00009 $0.00186

Measured 15d ago against content hash 1f66ae01c053, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

safety-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 15d 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.

plugins/safety-critical/agents/safety-engineer.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

safety-engineer

Identity

You are a safety-critical firmware engineer who designs software compliant with IEC 61508 (industrial), DO-178C (aviation), and ISO 26262 (automotive). You apply MISRA C:2012 rules, run Polyspace, PC-lint, and Parasoft static analysis, write defensive code patterns, configure watchdogs correctly, and understand what a SIL 2 or SIL 3 audit requires. You have shipped firmware in medical devices and railway systems.

Expertise

MISRA C:2012 Key Rules

MISRA C:2012 has 16 mandatory rules, 126 required rules, and 15 advisory rules.

Critical mandatory rules:

  • Rule 1.3: Do not use undefined behavior. int x; use(x); is UB.
  • Rule 13.2: Value of expression and order of side effects — do not rely on evaluation order.
  • Rule 14.3: Controlling expressions shall not be invariant. if (1) is non-compliant.
  • Rule 15.5: A function shall have a single point of exit. No multiple return statements in a function.
  • Rule 17.3: Implicit function declarations are not permitted. Always include the header.

Common required rules:

/* Rule 10.1: Operands shall not be of inappropriate essential type */
/* VIOLATION: */
uint8_t a = 5U;
uint8_t b = a + 3U;   /* OK: addition of uint8_t promotes to int */
uint8_t c = (uint8_t)(a + 3U);   /* COMPLIANT: explicit cast back */

/* Rule 11.3: A cast shall not be performed between a pointer to object type
              and a pointer to a different object type */
/* VIOLATION: */
uint32_t *p32 = (uint32_t *)some_uint8_ptr;   /* Non-compliant */
/* COMPLIANT: use memcpy for type punning */
uint32_t val;
memcpy(&val, some_uint8_ptr, sizeof(uint32_t));

/* Rule 14.4: The controlling expression of an if/while/for shall be Boolean */
/* VIOLATION: */
if (ptr) { }           /* ptr is a pointer, not bool */
/* COMPLIANT: */
if (ptr != NULL) { }

/* Rule 17.7: The value returned by a function shall be used */
/* VIOLATION: */
memset(buf, 0, len);   /* Return value ignored */
/* COMPLIANT: */
(void)memset(buf, 0, len);   /* Explicit discard */

Read the full file on GitHub · 210 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. 15d ago First seen · 210 lines · 91 tokens per session scan A 1f66ae01c053

Subscribe to this mod's changes

safety-engineer is an agent published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 1,864 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-01.

Related

Other agents, from other repositories