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.
npx skills add Midstall/claude-for-hardware --skill firmware-boot-chaingit clone --depth 1 https://github.com/Midstall/claude-for-hardwareWrote 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.
[](https://agentmods.dev/skills/midstall/claude-for-hardware/firmware-boot-chain)<a href="https://agentmods.dev/skills/midstall/claude-for-hardware/firmware-boot-chain"><img src="https://agentmods.dev/badge/skills/midstall/claude-for-hardware/firmware-boot-chain/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.
<a href="https://agentmods.dev/skills/midstall/claude-for-hardware/firmware-boot-chain"><img src="https://agentmods.dev/badge/skills/midstall/claude-for-hardware/firmware-boot-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01162 |
| Opus 5 | $0.00029 | $0.00581 |
| Sonnet 5 | $0.00012 | $0.00232 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
firmware-boot-chain 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firmware Boot Chain
Overview
A boot chain is a relay of stages, each responsible for setting up just enough state to hand control to the next: ROM to firmware (SBI/UEFI), firmware to bootloader, bootloader to OS. Every handoff has a contract: where the next stage lives, what registers/tables it expects, and what memory is already set up.
Core principle: Each stage owns a contract with the next. Most boot failures are a broken contract at exactly one handoff, so isolate which handoff fails before theorizing about the stage itself.
When to Use
- Writing or porting firmware (RISC-V SBI, UEFI services, ACPI table provision)
- Chaining a bootloader (Limine, GRUB, U-Boot) into an OS kernel
- A stage loads but the next never starts, or starts and immediately faults
- Adding measured boot / TPM PCR extension to the chain
- Discovering peripherals from a device tree or ACPI at firmware time
Map The Handoffs First
Write down the relay before debugging:
ROM -> firmware (SBI/UEFI) -> bootloader -> OS kernel
provides: SBI calls, loads: expects: a0=hartid,
memory map, ACPI/DTB kernel+initrd a1=DTB/ACPI ptr, MMU off
For each arrow, name: the entry address, the register/pointer contract, and the memory/translation state. The failing arrow is your bug location.
Firmware Responsibilities
- Provide the platform description. Hand the next stage a device tree (DTB) or ACPI tables describing memory, CPUs, and peripherals. Probe peripherals from this description rather than hardcoding addresses, so one firmware serves multiple board memory maps.
- Set the entry contract precisely. RISC-V convention passes hartid and a pointer to the platform description in fixed registers; get them exactly right. The next stage trusts them blindly.
- Build-time configure the memory base. RAM base and the firmware's own load address differ per board (for example external DRAM at a high base on one board, on-chip SRAM on another). Make these build-time parameters, not constants buried in one file.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 75 lines · 58 tokens per session scan A 10f5bb5e22b5
firmware-boot-chain is a skill published in the GitHub repository Midstall/claude-for-hardware (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,162 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
tia-doctor
Manual, read-only prerequisite probe for TIA Portal V21 and its modular Openness API, with optional Python TIA Scripting and TIA MCP checks.
routeros-mac-telnet
MAC-Telnet protocol (MikroTik Layer-2 terminal/exec over UDP 20561) wire format, session handshake, and MD5 + MTWEI (EC-SRP) authentication. Use when: implementing or debugging a MAC-Telnet client/server, reaching a RouterOS device by MAC address without IP, parsing MAC-Telnet packets, understanding the WinBox-style…
routeros-syntax-inspection
Inspecting and validating RouterOS command/script syntax against a live device via /console/inspect (highlight, completion, syntax, child) and :parse IL. Use when: validating RouterOS commands before execution, explaining or linting RouterOS scripts, building syntax-aware tooling (LSP servers, validators, agent…
routeros-sniffer
RouterOS packet capture and TZSP streaming for protocol debugging. Use when: capturing packets on RouterOS, setting up /tool/sniffer, streaming live traffic via TZSP, using firewall mangle action=sniff-tzsp, debugging network protocols on MikroTik, receiving TZSP with Wireshark or tshark, saving pcap files from…
8051-mcu-debug
Use when debugging 8051-compatible microcontrollers, 51 MCU firmware, STC download issues, Keil C51 projects, interrupts, timers, UART, or startup failures.
cortex-m-debug
Use when debugging Cortex-M microcontrollers, firmware bring-up, SWD/JTAG sessions, faults, startup code, or flashing failures.