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 ming-14/PTY-Agent --skill windows-debugginggit clone --depth 1 https://github.com/ming-14/PTY-AgentWrote 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/ming-14/pty-agent/windows-debugging)<a href="https://agentmods.dev/skills/ming-14/pty-agent/windows-debugging"><img src="https://agentmods.dev/badge/skills/ming-14/pty-agent/windows-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/ming-14/pty-agent/windows-debugging"><img src="https://agentmods.dev/badge/skills/ming-14/pty-agent/windows-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 | $0.00104 | $0.01796 |
| Opus 5.5 | $0.00042 | $0.00718 |
| Sonnet 5.5 | $0.00021 | $0.00359 |
| Haiku 4.5 | $0.00010 | $0.00180 |
Grade A, and why
windows-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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Debugging Tools (本地免安装版)
本技能封装位于 windows-debugging\10.0.19041.5609\ 的 Windows 调试工具集(Debugging Tools for Windows,版本 10.0.19041.5609)。所有 .exe 均可直接运行,无需安装、无需管理员(内核调试除外)。
如果windows-debugging\10.0.19041.5609\什么都没有,请通知用户下载
关键路径
- 工具根目录(下文用
$TOOLS指代):windows-debugging\10.0.19041.5609\ - 命令行用户态调试器:
$TOOLS\cdb.exe - 内核调试器:
$TOOLS\kd.exe/$TOOLS\ntkd.exe - 崩溃抓取:
$TOOLS\adplus.exe - 堆/内存泄漏:
$TOOLS\umdh.exe - dump 校验:
$TOOLS\dumpchk.exe/$TOOLS\dumpexam.exe - 符号校验:
$TOOLS\symchk.exe - 进程列表/终止:
$TOOLS\tlist.exe/$TOOLS\list.exe/$TOOLS\kill.exe
符号服务器(最重要)
分析 dump 前必须配符号,否则堆栈全是 ???。微软公共符号服务器:
srv*C:\Symbols*https://msdl.microsoft.com/download/symbols
- 在 WinDbg 图形界面里:
File > Symbol File Path填入上面字符串;或命令窗口执行.sympath srv*C:\Symbols*https://msdl.microsoft.com/download/symbols然后.reload。 - 用
cdb/命令行时通过-y参数传入:-y "srv*C:\Symbols*https://msdl.microsoft.com/download/symbols"。 - 公司私有符号服务器把上面的 URL 换成内网
srv*地址即可。
场景 1:分析蓝屏 / 崩溃 dump(.dmp)
最常用、最自动化的流程:
- 用 WinDbg 打开 dump:
& "$TOOLS\windbg.exe" -z "C:\path\to\memory.dmp" - 打开后自动执行自动分析命令:
重点看输出里的!analyze -vBUGCHECK_CODE、BUGCHECK_STRING、大概率 culprit(Probably caused by)、以及STACK_TEXT调用栈。 - 若符号未加载,先设符号路径再
.reload,重跑!analyze -v。 - 常用辅助命令:
k/kP— 当前线程调用栈(含参数)lm— 列出已加载模块及符号状态!thread/!process— 线程/进程上下文(内核 dump)!irp— 查 IRP(驱动相关 BSOD 常用)dt nt!_EPROCESS— 查看结构体
非交互(命令行)一次性分析:用 cdb 把命令串通过 -c 传入,适合脚本批量:
& "$TOOLS\cdb.exe" -y "srv*C:\Symbols*https://msdl.microsoft.com/download/symbols" -z "C:\path\to\memory.dmp" -c "!analyze -v; q"
(末尾 q 表示分析完退出。)
场景 2:用 ADPlus 抓取进程崩溃 / 挂起
当目标程序还没崩溃、需要它在崩溃瞬间自动生成 dump 时:
- 崩溃(Crash)模式:
或按 PID:& "$TOOLS\adplus.exe" -crash -pn <进程名.exe> -o "C:\dumps"-p <PID>。ADPlus 会挂一个调试器在进程上,进程一崩就写 mini/full dump 到-o目录。 - 挂起(Hang)模式(进程卡死无响应):
& "$TOOLS\adplus.exe" -hang -pn <进程名.exe> -o "C:\dumps" - 常见附加参数:
-fullonfirst第一次异常就抓 full dump;-quiet静默(适合脚本)。 - 注意:ADPlus 运行期间会拖慢目标进程;抓完用
kill/结束调试器即可释放。
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 · 124 lines · 104 tokens per session scan A a670229c5ae9
windows-debugging is a skill published in the GitHub repository ming-14/PTY-Agent (2 stars, last pushed 15d ago), licensed MIT. It adds 104 tokens to every session and 1,796 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
hqe
Comprehensive codebase health auditing, remediation, and verification skill based on the canonical HQE Protocol v5.0.0.
claw-admin
Claw system administration: service management, IM connections, logs, cron, and workspace diagnostics. Use when the user asks to manage claw services, connect/disconnect IM platforms, view logs, or perform system-wide operations.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
optimize
Review code for efficiency and performance. Triggered by "/optimize" when user wants to identify bottlenecks or improve performance.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
sivtr-memory
Retrieve shared local work memory: terminal activity, AI conversation history, prior decisions, validation evidence, debugging trails, recaps, and handoff context. Use before asking the user to repeat local work context.