agentmods.dev

openocd-jlink-stlink-debug

openocd-jlink-stlink-debug is a skill for Claude Code, Codex from easyzoom/aix-skills. It costs 53 tokens per session (2,006 once invoked), scanned A, original, MIT.

A guide for diagnosing connections between an embedded board and debugging probes such as J-Link, ST-Link, or CMSIS-DAP. It covers SWD and JTAG wiring, reset behavior, probe settings, flash programming, and GDB attachment.

In plain words
What is it for?
Use it when you cannot connect to, halt, reset, flash, erase, verify, or inspect an MCU with OpenOCD, a probe, or GDB.
Why use it?
A debugger may fail because of power, wiring, reset settings, firmware, or target configuration—not necessarily because of the application code. The guide separates these possible causes.

Skill for Claude CodeCodex

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

not rated 31repo 1mo ago A scan 53 tokens original MIT

Good fit Use it when you cannot connect to, halt, reset, flash, erase, verify, or inspect an MCU with OpenOCD, a probe, or GDB.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/easyzoom/aix-skills/openocd-jlink-stlink-debug
View source ↗ easyzoom/aix-skills
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 openocd-jlink-stlink-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 openocd-jlink-stlink-debug

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/easyzoom/aix-skills/openocd-jlink-stlink-debug"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/openocd-jlink-stlink-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,006 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 $0.00053 $0.02006
Opus 5 $0.00026 $0.01003
Sonnet 5 $0.00011 $0.00401
Haiku 4.5 $0.00005 $0.00201

Measured 10d ago against content hash ac367b33e40f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

openocd-jlink-stlink-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/openocd-jlink-stlink-debug/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Use this skill to debug probe sessions by separating physical wiring, probe firmware, target voltage, reset strategy, transport, target script, flash algorithm, and GDB behavior. Probe failures are often reset or adapter issues.

When To Use

Use this skill when:

  • The user cannot connect, halt, reset, flash, erase, verify, or attach with OpenOCD, J-Link, ST-Link, CMSIS-DAP, pyOCD, or GDB.
  • The issue involves SWD/JTAG wiring, adapter speed, reset config, target scripts, flash loaders, protected devices, semihosting, RTT, or multicore.
  • The same firmware behaves differently under debugger and standalone boot.

Do not use this skill for application fault analysis after a stable debug session exists. Use the architecture-specific debug skill then. For flash download failures focused on erase/program/verify, use mcu-flashing-debug.

First Questions

Ask for:

  • Probe model, firmware version, debugger tool, target MCU/SoC, board, and OS.
  • Wiring: VTref, GND, SWDIO/TMS, SWCLK/TCK, nRST/SRST, SWO, and power ownership.
  • Exact command, the -f interface/*.cfg and -f target/*.cfg scripts, adapter speed, transport select, and full log.
  • Reset mode, boot pins, readout protection (STM32 RDP), low-power state, and external flash.
  • Whether connect-under-reset, halt-after-reset, or attach-to-running is needed.

Launch Reference

  • ST-Link: openocd -f interface/stlink.cfg -f target/stm32f4x.cfg (stlink.cfg is the hla driver; use target/stm32f1x.cfg, stm32h7x.cfg, nrf52.cfg etc. for other parts).
  • J-Link: openocd -f interface/jlink.cfg -c "transport select swd" -f target/stm32f4x.cfg.
  • CMSIS-DAP/DAPLink: openocd -f interface/cmsis-dap.cfg -c "transport select swd" -f target/stm32f1x.cfg.
  • Force JTAG instead of SWD: -c "transport select jtag" (note stlink.cfg hla only supports hla_swd/hla_jtag).
  • Set speed before target script: -c "adapter speed 1000" (kHz; deprecated alias adapter_khz). Pick a probe by serial with -c "adapter serial <SN>" (older: hla_serial).
  • Default TCP ports: GDB 3333, Telnet monitor 4444, Tcl 6666.

Read the full file on GitHub · 161 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 · 161 lines · 53 tokens per session scan A ac367b33e40f

Subscribe to this mod's changes

openocd-jlink-stlink-debug is a skill published in the GitHub repository easyzoom/aix-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 2,006 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.

DebuggingHardware and IoTagent-skillsai-agentsai-workflowsautomationclaude-skillscortex-m
Related

Other skills, from other repositories

container-home

Answer questions, assist with planning, and help with design decisions for Mick's off-grid shipping container lake home project. Trigger when the user mentions the container home, lake home, Stewart County, LBL, the expansion, solar system, septic permitting, or retirement property.

mickpletcher/AI-Skills · 57 tokens

eide

A build tool for EIDE projects, an embedded-development extension for Visual Studio Code. It finds EIDE project settings and builds firmware using ARM CC or GCC.

zhinkgit/embeddedskills · 151 tokens

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

workflow

A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.

zhinkgit/embeddedskills · 88 tokens

investigate

Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.

oliver-kriska/claude-elixir-phoenix · 40 tokens

narrow-bare-rescue

Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.

oliver-kriska/claude-elixir-phoenix · 40 tokens