mcu-flashing-debug

mcu-flashing-debug is a skill for Claude Code, Codex from easyzoom/aix-skills. It costs 32 tokens per session (917 once invoked), scanned A, original, MIT.

A guide for diagnosing failures when firmware is erased, written, checked, or started on a microcontroller. It covers the board, programmer, connection, boot mode, protection settings, and firmware file.

In plain words
What is it for?
Use it when tools such as ST-Link, J-Link, CMSIS-DAP, OpenOCD, or vendor programmers report connection, timeout, voltage, protection, or verification errors.
Why use it?
It separates connection, erase, programming, verification, and reset problems so the wrong fix is less likely to damage or lock the device.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when tools such as ST-Link, J-Link, CMSIS-DAP, OpenOCD, or vendor programmers report connection, timeout, voltage, protection, or verification errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/easyzoom/aix-skills/mcu-flashing-debug
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.

Any agent
npx skills add easyzoom/aix-skills --skill mcu-flashing-debug
Clone the repo
git clone --depth 1 https://github.com/easyzoom/aix-skills

Made for: Claude Code, Codex.

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 mcu-flashing-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/easyzoom/aix-skills/mcu-flashing-debug/github.svg)](https://agentmods.dev/skills/easyzoom/aix-skills/mcu-flashing-debug)
Your own site
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/mcu-flashing-debug"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/mcu-flashing-debug/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 mcu-flashing-debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/mcu-flashing-debug"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/mcu-flashing-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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 $0.00032 $0.00917
Opus 5 $0.00016 $0.00458
Sonnet 5 $0.00006 $0.00183
Haiku 4.5 $0.00003 $0.00092

Measured 10d ago against content hash f41c468035ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcu-flashing-debug 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 10d 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.

skills/mcu-flashing-debug/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCU Flashing Debug

Overview

Use this skill to debug MCU programming failures safely. Separate connection, erase, program, verify, and reset problems before recommending mass erase, option byte changes, security unlock, or boot configuration changes.

When To Use

Use this skill when:

  • Firmware cannot be downloaded or flashed to an MCU.
  • The programmer reports connect, erase, program, verify, timeout, locked, protected, or target voltage errors.
  • The user mentions ST-Link, J-Link, CMSIS-DAP, OpenOCD, pyOCD, STC-ISP, WCH-Link, Nu-Link, vendor programmers, boot pins, ISP, IAP, DFU, or UART bootloader.

Do not use this skill for application-level bugs after a confirmed successful program/verify/run cycle. For probe-specific debugging (OpenOCD scripts, J-Link config, adapter speed), use openocd-jlink-stlink-debug.

First Questions

Ask for:

  • MCU part number and board.
  • Programmer/probe and connection method.
  • Tool name and exact error output.
  • Firmware artifact path/type: ELF, HEX, BIN, IHX, UF2, or vendor package.
  • Whether erase, program, verify, and reset are separate steps in the tool output.
  • Target voltage, reset wiring, boot pins, and whether the board is externally powered.

Workflow

  1. Classify the failing step. Do not treat "download failed" as one problem. Identify connect, erase, program, verify, reset, or run failure.

  2. Confirm physical and electrical basics. Check power, ground, target voltage sense, reset line, boot pins, and signal wiring before changing software.

  3. Confirm tool-target match. Verify exact chip model, flash algorithm, probe interface, target config, and firmware address.

  4. Lower risk before increasing force. Try lower adapter speed, connect-under-reset, separate erase/program/verify, and fresh rebuild before mass erase.

  5. Preserve logs. Capture programmer output and avoid repeated blind retries.

  6. Ask before destructive operations. Mass erase, security unlock, option byte writes, readout protection changes, bootloader erase, and config fuse changes require explicit approval.

Read the full file on GitHub · 108 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. 10d ago First seen · 108 lines · 32 tokens per session scan A f41c468035ae

Subscribe to this mod's changes

mcu-flashing-debug is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 917 once invoked, about $0.0002 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.