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 easyzoom/aix-skills --skill cmbacktrace-integrationgit clone --depth 1 https://github.com/easyzoom/aix-skillsWrote 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/easyzoom/aix-skills/cmbacktrace-integration)<a href="https://agentmods.dev/skills/easyzoom/aix-skills/cmbacktrace-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/cmbacktrace-integration/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/easyzoom/aix-skills/cmbacktrace-integration"><img src="https://agentmods.dev/badge/skills/easyzoom/aix-skills/cmbacktrace-integration.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 | $0.00037 | $0.00752 |
| Opus 5.5 | $0.00015 | $0.00301 |
| Sonnet 5.5 | $0.00007 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
cmbacktrace-integration 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CmBacktrace Integration
Overview
Use this skill to integrate CmBacktrace as a Cortex-M crash diagnosis tool. The key is to preserve fault context, provide correct firmware metadata, route output safely, and verify that backtraces map to the running ELF.
When To Use
Use this skill when:
- The target is Cortex-M and the user wants automatic fault diagnosis or stack backtraces.
- The issue involves HardFault, fault handlers, register dumps, firmware name/version/hardware version, or crash logs.
- The project uses or plans to use CmBacktrace.
Do not use this skill for non-Cortex-M faults. Use embedded-fault-debug or the architecture-specific debug skill instead.
First Questions
Ask for:
- MCU/core, compiler, optimization level, and build flags.
- Fault handler code and whether the system resets immediately.
- Output backend for crash text: UART, RTT, flash, EasyLogger, shell, or custom.
- Firmware metadata values and where they are defined.
- Whether the ELF/MAP file matching the running image is available.
- Current fault output or absence of output.
Integration Checklist
-
Integrate in the fault path. Call CmBacktrace from the HardFault/fault handling path before reset and before clearing fault state.
-
Provide metadata. Firmware name, hardware version, software version, and platform identifiers should be meaningful enough for field logs.
-
Keep output safe. Crash output must not block forever, allocate heavily, or depend on services that may be corrupted.
-
Match symbols. Ensure the saved crash output can be mapped to the exact ELF/MAP file used to build the flashed image.
-
Account for compiler behavior. Optimization, frame pointer omission, link-time optimization, and stripped symbols can reduce backtrace quality.
-
Verify with a controlled fault. Trigger a known null pointer or assert in a lab build, then confirm the report identifies the expected function.
Porting Checks
- Fault handler does not reset before CmBacktrace runs.
- Stack pointer and fault stack frame are still valid when called.
- Output route is initialized early or has a crash-safe fallback.
- RTOS task stack ranges are known if task-aware backtracing is expected.
- Watchdog timeout is long enough to emit crash data or is handled intentionally.
- Crash logs stored to flash do not erase unrelated data without approval.
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 · 93 lines · 37 tokens per session scan A b97d8dbb039e
cmbacktrace-integration is a skill published in the GitHub repository easyzoom/aix-skills (38 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 752 once invoked, about $0.0001 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
routeros-mac-telnet
MAC-Telnet protocol (MikroTik Layer-2 terminal/exec over UDP 20561) wire format, session handshake, and MD5 + MTWEI (EC-SRP) authentication. Use when: implementing or debugging a MAC-Telnet client/server, reaching a RouterOS device by MAC address without IP, parsing MAC-Telnet packets, understanding the WinBox-style…
routeros-syntax-inspection
Inspecting and validating RouterOS command/script syntax against a live device via /console/inspect (highlight, completion, syntax, child) and :parse IL. Use when: validating RouterOS commands before execution, explaining or linting RouterOS scripts, building syntax-aware tooling (LSP servers, validators, agent…
routeros-sniffer
RouterOS packet capture and TZSP streaming for protocol debugging. Use when: capturing packets on RouterOS, setting up /tool/sniffer, streaming live traffic via TZSP, using firewall mangle action=sniff-tzsp, debugging network protocols on MikroTik, receiving TZSP with Wireshark or tshark, saving pcap files from…
tia-doctor
Manual, read-only prerequisite probe for TIA Portal V21 and its modular Openness API, with an optional Python TIA Scripting check.
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…
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.