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.
git 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/commands/midstall/claude-for-hardware/hw-bringup)<a href="https://agentmods.dev/commands/midstall/claude-for-hardware/hw-bringup"><img src="https://agentmods.dev/badge/commands/midstall/claude-for-hardware/hw-bringup.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00381 |
| Opus 5 | $0.00006 | $0.00191 |
| Sonnet 5 | $0.00002 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
hw-bringup 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 8d 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.
What it actually says
The user is bringing up bare-metal code, firmware, or an FPGA on real hardware and it will not come up. Context and symptom: $ARGUMENTS
Invoke the relevant skill for the situation: bare-metal-bringup for kernel/bare-metal on a new arch or board, fpga-bringup for loading and driving a bitstream over JTAG/GPIO, firmware-boot-chain for a firmware or bootloader handoff. Then drive the bring-up as a ladder, proving each rung before climbing:
- Get one known byte out a UART first. Until there is output, the rest is blind.
- Stack and BSS valid and correctly placed.
- Trap vectors installed and proven by a deliberate trap (mind part-specific vector alignment).
- Architectural timer init before any kernel timer that divides by its frequency.
- Address translation: identity-map then enable (watch for silent overlapping-PMP rejection).
- Interrupts: right enable model; pollers on a shared line must suppress.
- Userspace/syscalls: preserve exactly what the ABI promises.
For FPGA config: prove the transport first (IDCODE, IR width), read back DONE rather than trusting the shift, and confirm the bitstream clock is at or below real Fmax. For a boot chain: map the handoffs and find the failing arrow.
Localize the failing rung with evidence before proposing any fix. Treat "works in sim, dead on hardware" or "works in TCG, dies in KVM" as a real ordering or state-save bug, not a tooling quirk. Add a raw output byte at the suspect transition to bisect.
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.
- 8d ago First seen · 21 lines · 12 tokens per session scan A f25905290343
hw-bringup is a command published in the GitHub repository Midstall/claude-for-hardware (20 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 381 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 2026-08-30.
Other commands, from other repositories
debug
A command-line debugging toolkit for embedded programs using J-Link or OpenOCD, tools that connect a computer to a microcontroller for inspection.
la
A command for capturing and decoding signals with a Saleae logic analyzer, a device that records electrical digital signals over time. It supports buses such as UART, SPI, and I2C, which are common ways chips communicate with peripherals.
map
A parser for Keil compiler map files, which are build reports describing where program code and data are placed in memory. It reports object sizes, memory regions, symbols, and stack or heap details.
verify
An embedded-device verification workflow that checks a development step through building, flashing firmware, debugging with J-Link, and reading serial logs. Firmware is software that runs directly on a microcontroller or other device.
health
One-line reliability verdict (OK / DEGRADED / FAILING) for Claude Code usage.
replay
Summarize one Agent Monitor session by id — header plus a concise transcript recap.