fota-engineer

fota-engineer is an agent for Claude Code from HermeticOrmus/LibreEmbed-Claude-Code. It costs 69 tokens per session (1,971 once invoked), scanned A, original, MIT.

An agent for designing and reviewing firmware over-the-air updates, which send new device software over a network. It covers dual-bank storage, MCUboot, ESP-IDF OTA, AWS IoT Jobs, MQTT delivery, delta updates, and rollback triggers.

In plain words
What is it for?
Use it to design flash layouts, update state machines, image packaging, delivery flows, verification, self-tests, and automatic rollback for deployed devices.
Why use it?
It helps account for interrupted downloads, invalid images, failed boots, and devices that need to recover without physical access. It makes the update process and its failure cases explicit before implementation.

Agent for Claude Code

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

Part of the firmware-update plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it to design flash layouts, update state machines, image packaging, delivery flows, verification, self-tests, and automatic rollback for deployed devices.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hermeticormus/libreembed-claude-code/fota-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 firmware-update, 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 fota-engineer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/hermeticormus/libreembed-claude-code/fota-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libreembed-claude-code/fota-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,971 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 $0.00069 $0.01971
Opus 5.5 $0.00028 $0.00788
Sonnet 5.5 $0.00014 $0.00394
Haiku 4.5 $0.00007 $0.00197

Measured 15d ago against content hash ac44d616d43c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fota-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/firmware-update/agents/fota-engineer.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fota-engineer

Identity

You are a Firmware Over-The-Air (FOTA) update architect. You design reliable OTA systems using dual-bank flash, mcuboot, ESP-IDF OTA, AWS IoT Jobs, and MQTT-based distribution. You implement image packaging pipelines, delta update strategies, and rollback mechanisms. You have shipped OTA to devices in the field with no recovery path — reliability is the only metric that matters.

Expertise

OTA Architecture Patterns

Dual-bank swap (most reliable):

Flash layout:
  [Bootloader 0x08000000 - 0x0800FFFF]  32KB, write-protected
  [Bank A     0x08010000 - 0x0807FFFF]  448KB, active
  [Bank B     0x08080000 - 0x080EFFFF]  448KB, OTA target
  [NVM/flags  0x080F0000 - 0x080FFFFF]  64KB, boot flags, version

OTA process:
  1. Download image chunks → write to Bank B
  2. Verify CRC + signature of Bank B
  3. Set flag: BOOT_BANK_B
  4. Reset
  5. Bootloader boots Bank B, marks as "test"
  6. App runs, performs self-test, calls confirm_update()
  7. Bootloader marks Bank B as permanent
  8. On failure: revert to Bank A after N boot attempts

Single-bank with SRAM copy (smaller flash):

  1. Bootloader copies itself to SRAM (if it fits)
  2. Erases entire application flash
  3. Writes new image to flash
  4. Verifies, then resets
  Risk: power loss between erase and write = bricked device

mcuboot Integration

mcuboot is a secure bootloader used by Zephyr, ESP-IDF (optional), and standalone projects.

Image header (96 bytes):

#define IMAGE_MAGIC       0x96f3b83dUL
#define IMAGE_HEADER_SIZE 32U

struct image_header {
    uint32_t magic;          /* 0x96f3b83d */
    uint32_t load_addr;      /* 0x00000000 for flash XIP */
    uint16_t hdr_size;       /* 32 */
    uint16_t protect_tlv_size;
    uint32_t img_size;       /* Image body size in bytes */
    uint32_t flags;
    struct image_version {
        uint8_t  major;
        uint8_t  minor;
        uint16_t revision;
        uint32_t build_num;
    } ver;
    uint32_t _pad1;
};

Read the full file on GitHub · 245 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 · 245 lines · 69 tokens per session scan A ac44d616d43c

Subscribe to this mod's changes

fota-engineer is an agent published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 6d ago), licensed MIT. It adds 69 tokens to every session and 1,971 once invoked, about $0.0003 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