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 ptsilivis/autonomousguy --skill embedded-debugginggit clone --depth 1 https://github.com/ptsilivis/autonomousguyWrote 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/ptsilivis/autonomousguy/embedded-debugging)<a href="https://agentmods.dev/skills/ptsilivis/autonomousguy/embedded-debugging"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/embedded-debugging/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/ptsilivis/autonomousguy/embedded-debugging"><img src="https://agentmods.dev/badge/skills/ptsilivis/autonomousguy/embedded-debugging.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 | $0.00208 | $0.04164 |
| Opus 5.5 | $0.00083 | $0.01666 |
| Sonnet 5.5 | $0.00042 | $0.00833 |
| Haiku 4.5 | $0.00021 | $0.00416 |
Grade A, and why
embedded-debugging 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 1mo 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Embedded Debugging
Context
You are a senior embedded automotive engineer who has resolved hundreds of field defects and live-fault scenarios in AUTOSAR ECU software on ARM Cortex-M/R targets. You debug with GDB, Lauterbach TRACE32, Vector CANalyzer, and AUTOSAR OS trace tools. You separate symptoms from causes, work from observable signatures, and give concrete advice — specific commands, register reads, and code patterns — never generic "add logging" suggestions. You know the common failure patterns in embedded C (race conditions, stack overflow, integer wrap, uninitialised state), AUTOSAR (RTE comm errors, BSW misconfig, task overrun), and vehicle integration (CAN timeout, signal plausibility, ECU mode mismatch).
Instructions
Decide platform first, and state it in the output:
- Default: Classic AUTOSAR (CP) - ARM Cortex-M/R, AUTOSAR OS, HardFault/watchdog/Dem, GDB/TRACE32. Use everything below.
- Switch to Adaptive AUTOSAR (AP) if the input names POSIX/Linux/QNX, ara::, C++, segfault/SIGSEGV, core dump, or Execution/State Management. AP faults differ: POSIX process crashes (segfault, abort, uncaught exception), Execution Management restart loops, ara::com service-not-available, ara::per storage errors, thread races, memory leaks/OOM. Tools are gdb on the application processor, core dumps, ara::log, perf/valgrind/AddressSanitizer - not TRACE32-on-MCU, CFSR decode, or OS ProtectionHook. For AP, use the fault catalog and step layouts in
references/adaptive-ap.md, keeping the same output structure.
Then decide mode from the input:
- A free-text problem report, ticket, or field complaint with conditions/frequency → Problem-report triage.
- A specific fault signature (HardFault address, watchdog reset cause, OS error code, exact wrong value, stack trace) → Targeted fault debugging.
- Mixed → triage first to narrow hypotheses, then targeted debugging on the leading hypothesis.
Operating principles (apply to every response)
What ships with it
2 files 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.
- 1mo ago First seen · 251 lines · 208 tokens per session scan A 6d1cf95439a5
embedded-debugging is a skill published in the GitHub repository ptsilivis/autonomousguy (35 stars, last pushed 3mo ago), licensed MIT. It adds 208 tokens to every session and 4,164 once invoked, about $0.0008 per session on Opus 5.5. 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
embedded-debugging
Debug embedded firmware on real hardware through the jlink-mcp server — crashes, hangs, peripheral misconfiguration, silent devices. Covers loading ELF symbols for source-level backtraces, supplying an SVD for named peripheral fields, and the halt/read/resume discipline. Use whenever debugging a microcontroller over a…
nuedc
A workflow for solving China’s National Undergraduate Electronic Design Contest (TI Cup), from understanding a task to designing circuits, writing code, compiling, flashing, and debugging. It can generate wiring diagrams and support MCU, FPGA, simulation, and PCB work, but physical wiring, soldering, and instrument operation still need a person.
serial-debug
CLI-first serial port debugging and macro automation with serial-mcp-server for Codex and Claude Code. Use when working with UART or USB-serial devices, listing serial ports, probing STM32/Arduino/ESP32 boards, writing or reading serial data, running JSON serial macros, controlling RTS/DTR, or using serial-mcp-server…
debug-gdb-openocd
An OpenOCD and GDB debugging tool for embedded firmware. OpenOCD connects a computer to many microcontroller debug probes, and GDB is used to inspect and control the program.
flash-jlink
A tool for using a SEGGER J-Link probe to program embedded devices and capture RTT logs. A J-Link probe connects a computer to a microcontroller for programming and debugging; RTT is a way to read device logs through that connection.
serial-monitor
An embedded-device serial monitoring skill for identifying the correct serial port, collecting logs with included scripts, and examining firmware behavior.