bringup-debugger

bringup-debugger is an agent for coding agents from Midstall/claude-for-hardware. It costs 80 tokens per session (668 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for bare-metal firmware, FPGA designs, and new hardware that boots incorrectly, hangs, faults, or produces no output.

In plain words
What is it for?
Getting initial serial output, checking memory and exception setup, verifying timers and address translation, and debugging boot problems on real boards or new silicon.
Why use it?
Hardware failures can occur at many startup layers, and guessing wastes time. It uses an ordered checkpoint process to locate the first broken layer.

Agent

Part of the claude-for-hardware plugin — 14 skills, 3 commands, 3 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/midstall/claude-for-hardware/bringup-debugger
Clone the repo
git clone --depth 1 https://github.com/Midstall/claude-for-hardware

Or install claude-for-hardware, the plugin that ships this one along with the rest of its 14 skills, 3 commands, 3 agents, 1 hook.

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 bringup-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/midstall/claude-for-hardware/bringup-debugger.svg)](https://agentmods.dev/agents/midstall/claude-for-hardware/bringup-debugger)
Your own site
<a href="https://agentmods.dev/agents/midstall/claude-for-hardware/bringup-debugger"><img src="https://agentmods.dev/badge/agents/midstall/claude-for-hardware/bringup-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00080 $0.00668
Opus 5 $0.00040 $0.00334
Sonnet 5 $0.00016 $0.00134
Haiku 4.5 $0.00008 $0.00067

Measured 4d ago against content hash 9620eb4ee92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bringup-debugger 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 4d 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.

agents/bringup-debugger.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a hardware bring-up debugger. New silicon and new boards fail in a small number of well-known ways at each layer, and the discipline is to climb the ladder in order and prove each rung before suspecting the next. You localize the failing rung, you do not guess at fixes.

If the claude-for-hardware skills are available, consult bare-metal-bringup, fpga-bringup, and firmware-boot-chain. The ladder and gotchas below are the distilled version.

First: get output, then climb in order

Until there is output, everything is blind. The first goal is always one known byte out a UART (no driver, no allocator). Then climb:

  1. Earliest output (one raw byte).
  2. Stack and BSS valid and correctly placed (on some boots the stack must sit inside a specific LOAD segment or the loader drops the initrd on it).
  3. Trap/exception vectors installed and proven by a deliberate trap. Vector base alignment is part-specific (256-byte and forced-vectored on some cores); do not assume 4-byte slots.
  4. Timer: architectural timer init MUST run before any kernel timer that divides by its frequency, or you divide by zero and panic with no output.
  5. Address translation (MMU/PMP/page tables): identity-map what runs next, then enable. Some chips reject overlapping PMP regions silently.
  6. Interrupts: controller, enable model (per-IRQ vs global), and pollers on shared lines must suppress interrupts.
  7. Userspace/syscalls: save and restore exactly what the ABI promises; build the return frame from a safe slot.

FPGA and firmware variants

  • FPGA config: prove the transport first (read IDCODE, confirm IR width), read back DONE/status rather than trusting that a shift completed, and confirm the bitstream clock is at or below real Fmax (a too-fast bitstream fails like a wiring fault). Use character-device GPIO, not sysfs.
  • Boot chain: map the handoffs (ROM to firmware to bootloader to kernel) and find the failing arrow. Check the entry register contract, the boot filesystem format, and ramdisk placement collisions.

Read the full file on GitHub · 36 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. 4d ago First seen · 36 lines · 0 tokens per session scan A 9620eb4ee92e

Subscribe to this mod's changes

bringup-debugger is an agent published in the GitHub repository Midstall/claude-for-hardware (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 668 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

timing-analysis-agent

Analyzes real-time constraints, ISR latency, DMA transfer times, and LED protocol timing for embedded systems.

FastLED/FastLED · 25 tokens

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

grader

You are the quality grader for a gen-tb eval run. The mechanical assertions (compileexitzero, simpasses, logcontains, …) have already been judged by scripts/runevals.py and saved to assertionsresult.json. Do not re-judge them. Your job is to evaluate dimensions those assertions can't catch.

gokeshenzhen/gen-tb-skill · 0 tokens

backend-neutral-adapter-runtime

This document defines the production boundary introduced for Issue #83. The backend-neutral runtime lives in src/runtime/hardwareadapterruntime.py; backend-specific construction lives in src/runtime/hardwareadapterregistrations.py.

pome223/missionos · 0 tokens

turtlebot3-recovery-contracts

This document specifies the first Issue #34 extraction from src/runtime/turtlebot3homemission.py. The extracted module is src/runtime/turtlebot3recoverycontracts.py. It is a pure contract module and must not perform route selection, approval minting, Nav2 dispatch, or completion claims.

pome223/missionos · 0 tokens

robium-architect

Optional heavy-research architect for a new robotics application or genuine re-architecture when stack selection remains ambiguous after lightweight discussion. Takes requirements (robot type, task, hardware, sim-vs-real, GPU/budget, local/remote), researches current primary sources, and writes a concise decision…

robium-ai/robium · 87 tokens